[docs]class BatchClient:
- """Client class for Speechmatics Batch ASR REST API.
+ """Client class for Speechmatics Batch ASR REST API.
This client may be used directly but must be closed afterwards, e.g.::
@@ -82,7 +82,7 @@ Source code for speechmatics.batch_client
"""
def __init__(self, connection_settings: ConnectionSettings):
- """Constructor method.
+ """Constructor method.
:param connection_settings: Connection settings for API
:type connection_settings: speechmatics.models.ConnectionSettings.
@@ -103,7 +103,7 @@ Source code for speechmatics.batch_client
self.api_client = None
[docs] def connect(self):
- """Create a connection to a Speechmatics Transcription REST endpoint"""
+ """Create a connection to a Speechmatics Transcription REST endpoint"""
self.api_client = httpx.Client(
base_url=self.connection_settings.url,
timeout=None,
@@ -121,7 +121,7 @@ Source code for speechmatics.batch_client
self.close()
[docs] def close(self) -> None:
- """
+ """
Clean up/close client connection pool.
This is required when using the client directly, but not required when
@@ -132,7 +132,7 @@ Source code for speechmatics.batch_client
self.api_client.close()
[docs] def send_request(self, method: str, path: str, **kwargs) -> httpx.Response:
- """
+ """
Send a request using httpx.Client()
:param method: HTTP request method
@@ -155,7 +155,7 @@ Source code for speechmatics.batch_client
return response
[docs] def list_jobs(self) -> List[Dict[str, Any]]:
- """
+ """
Lists last 100 jobs within 7 days associated with auth_token for the SaaS
or all of the jobs for the batch appliance.
@@ -171,7 +171,7 @@ Source code for speechmatics.batch_client
Dict[str, Any], BatchTranscriptionConfig, str, os.PathLike
],
) -> str:
- """
+ """
Submits audio and config for transcription.
:param audio: Audio file path or tuple of filename and bytes
@@ -194,7 +194,7 @@ Source code for speechmatics.batch_client
config_json = json.dumps(transcription_config)
else:
raise ValueError(
- """Job configuration must be a BatchTranscriptionConfig object,
+ """Job configuration must be a BatchTranscriptionConfig object,
a filepath as a string or Path object, or a dict"""
)
config_data = {"config": config_json.encode("utf-8")}
@@ -217,7 +217,7 @@ Source code for speechmatics.batch_client
job_id: str,
transcription_format: str = "json-v2",
) -> Union[bool, str, Dict[str, Any]]:
- """
+ """
Request results of a transcription job.
:param job_id: ID of previously submitted job.
@@ -261,7 +261,7 @@ Source code for speechmatics.batch_client
return response.text
[docs] def delete_job(self, job_id: str, force: bool = False) -> str:
- """
+ """
Delete a job. Must pass force=True to cancel a running job.
:param job_id: ID of previously submitted job.
@@ -295,7 +295,7 @@ Source code for speechmatics.batch_client
return False
[docs] def check_job_status(self, job_id: str) -> Dict[str, Any]:
- """
+ """
Check the status of a job.
:param job_id: ID of previously submitted job.
@@ -318,7 +318,7 @@ Source code for speechmatics.batch_client
[docs] def wait_for_completion(
self, job_id: str, transcription_format: str = "txt"
) -> Union[str, Dict[str, Any]]:
- """
+ """
Blocks until job is complete, returning a transcript in
the requested format.
@@ -373,7 +373,7 @@ Source code for speechmatics.batch_client
def _from_file(
self, path: Union[str, os.PathLike], filetype: str
) -> Union[Dict[Any, Any], Tuple[str, bytes]]:
- """Retrieve data from a file.
+ """Retrieve data from a file.
For filetype=="json", returns a dict
For filetype=="binary", returns a tuple of (filename, data)
"""
@@ -461,7 +461,7 @@ Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
diff --git a/docs/_modules/speechmatics/client.html b/docs/_modules/speechmatics/client.html
index d113f62..727fbe3 100644
--- a/docs/_modules/speechmatics/client.html
+++ b/docs/_modules/speechmatics/client.html
@@ -64,7 +64,7 @@ Source code for speechmatics.client
[docs]class WebsocketClient:
- """
+ """
Manage a transcription session with the server.
The best way to interact with this library is to instantiate this client
@@ -100,7 +100,7 @@ Source code for speechmatics.client
self._buffer_semaphore = asyncio.BoundedSemaphore
async def _init_synchronization_primitives(self):
- """
+ """
Used to initialise synchronization primitives that require
an event loop
"""
@@ -110,7 +110,7 @@ Source code for speechmatics.client
)
def _flag_recognition_started(self):
- """
+ """
Handle a
:py:attr:`speechmatics.models.ClientMessageType.SetRecognitionConfig`
message from the server.
@@ -120,7 +120,7 @@ Source code for speechmatics.client
self._recognition_started.set()
def _set_language_pack_info(self, language_pack_info: dict):
- """
+ """
Update the `language_pack_info` which is a subset of information from the
manifest in the language pack which we expose to end users via the
RecognitionStarted message.
@@ -128,7 +128,7 @@ Source code for speechmatics.client
self._language_pack_info = language_pack_info
[docs] def get_language_pack_info(self) -> dict:
- """
+ """
Get the `language_pack_info` which is a subset of information from the
manifest in the language pack which we expose to end users.
@@ -139,7 +139,7 @@ Source code for speechmatics.client
@json_utf8
def _set_recognition_config(self):
- """
+ """
Constructs a
:py:attr:`speechmatics.models.ClientMessageType.SetRecognitionConfig`
message.
@@ -153,7 +153,7 @@ Source code for speechmatics.client
@json_utf8
def _start_recognition(self, audio_settings):
- """
+ """
Constructs a
:py:attr:`speechmatics.models.ClientMessageType.StartRecognition`
message.
@@ -174,7 +174,7 @@ Source code for speechmatics.client
@json_utf8
def _end_of_stream(self):
- """
+ """
Constructs an
:py:attr:`speechmatics.models.ClientMessageType.EndOfStream`
message.
@@ -185,7 +185,7 @@ Source code for speechmatics.client
return msg
def _consumer(self, message):
- """
+ """
Consumes messages and acts on them.
:param message: Message received from the server.
@@ -222,7 +222,7 @@ Source code for speechmatics.client
raise TranscriptionError(message["reason"])
async def _producer(self, stream, audio_chunk_size):
- """
+ """
Yields messages to send to the server.
:param stream: File-like object which an audio stream can be read from.
@@ -250,7 +250,7 @@ Source code for speechmatics.client
yield self._end_of_stream()
async def _consumer_handler(self):
- """
+ """
Controls the consumer loop for handling messages from the server.
raises: ConnectionClosedError when the upstream closes unexpectedly
@@ -268,7 +268,7 @@ Source code for speechmatics.client
self._consumer(message)
async def _producer_handler(self, stream, audio_chunk_size):
- """
+ """
Controls the producer loop for sending messages to the server.
"""
await self._recognition_started.wait()
@@ -284,7 +284,7 @@ Source code for speechmatics.client
return
def _call_middleware(self, event_name, *args):
- """
+ """
Call the middlewares attached to the client for the given event name.
:raises ForceEndSession: If this was raised by the user's middleware.
@@ -297,7 +297,7 @@ Source code for speechmatics.client
raise
[docs] def update_transcription_config(self, new_transcription_config):
- """
+ """
Updates the transcription config used for the session.
This results in a SetRecognitionConfig message sent to the server.
@@ -309,7 +309,7 @@ Source code for speechmatics.client
self._transcription_config_needs_update = True
[docs] def add_event_handler(self, event_name, event_handler):
- """
+ """
Add an event handler (callback function) to handle an incoming
message from the server. Event handlers are passed a copy of the
incoming message from the server. If `event_name` is set to 'all' then
@@ -348,7 +348,7 @@ Source code for speechmatics.client
self.event_handlers[event_name].append(event_handler)
[docs] def add_middleware(self, event_name, middleware):
- """
+ """
Add a middleware to handle outgoing messages sent to the server.
Middlewares are passed a reference to the outgoing message, which
they may alter.
@@ -383,7 +383,7 @@ Source code for speechmatics.client
self.middlewares[event_name].append(middleware)
async def _communicate(self, stream, audio_settings):
- """
+ """
Create a producer/consumer for transcription messages and
communicate with the server.
Internal method called from _run.
@@ -412,7 +412,7 @@ Source code for speechmatics.client
raise exc
[docs] async def run(self, stream, transcription_config, audio_settings):
- """
+ """
Begin a new recognition session.
This will run asynchronously. Most callers may prefer to use
:py:meth:`run_synchronously` which will block until the session is
@@ -466,7 +466,7 @@ Source code for speechmatics.client
self.websocket = None
[docs] def stop(self):
- """
+ """
Indicates that the recognition session should be forcefully stopped.
Only used in conjunction with `run`.
You probably don't need to call this if you're running the client via
@@ -475,7 +475,7 @@ Source code for speechmatics.client
self._session_needs_closing = True
[docs] def run_synchronously(self, *args, timeout=None, **kwargs):
- """
+ """
Run the transcription synchronously.
:raises asyncio.TimeoutError: If the given timeout is exceeded.
"""
@@ -484,7 +484,7 @@ Source code for speechmatics.client
async def _get_temp_token(api_key):
- """
+ """
Used to get a temporary token from management platform api for SaaS users
"""
mp_api_url = os.getenv("SM_MANAGEMENT_PLATFORM_URL", "https://mp.speechmatics.com")
@@ -576,7 +576,7 @@ Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
diff --git a/docs/_modules/speechmatics/exceptions.html b/docs/_modules/speechmatics/exceptions.html
index 4fffcba..4362565 100644
--- a/docs/_modules/speechmatics/exceptions.html
+++ b/docs/_modules/speechmatics/exceptions.html
@@ -38,26 +38,26 @@ Source code for speechmatics.exceptions
[docs]class EndOfTranscriptException(Exception):
- """
+ """
Indicates that the transcription session has finished.
"""
[docs]class ForceEndSession(Exception):
- """
+ """
Can be raised by the user from a middleware or event handler
in order to force the transcription session to end early.
"""
@@ -138,7 +138,7 @@ Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
diff --git a/docs/_modules/speechmatics/helpers.html b/docs/_modules/speechmatics/helpers.html
index f77446f..746f5ec 100644
--- a/docs/_modules/speechmatics/helpers.html
+++ b/docs/_modules/speechmatics/helpers.html
@@ -44,7 +44,7 @@ Source code for speechmatics.helpers
[docs]def del_none(dictionary):
- """
+ """
Recursively delete from the dictionary all entries which values are None.
This function changes the input parameter in place.
@@ -63,17 +63,17 @@ Source code for speechmatics.helpers
[docs]def json_utf8(func):
- """A decorator to turn a function's return value into JSON"""
+ """A decorator to turn a function's return value into JSON"""
def wrapper(*args, **kwargs):
- """wrapper"""
+ """wrapper"""
return json.dumps(func(*args, **kwargs))
return wrapper
[docs]async def read_in_chunks(stream, chunk_size):
- """
+ """
Utility method for reading in and yielding chunks
:param stream: file-like object to read audio from
@@ -106,7 +106,7 @@ Source code for speechmatics.helpers
def _process_status_errors(error):
- """
+ """
Takes an httpx.HTTPSStatusError and prints in a useful format for CLI
:param error: the status error produced by the server for a request
@@ -215,7 +215,7 @@ Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
diff --git a/docs/_modules/speechmatics/models.html b/docs/_modules/speechmatics/models.html
index 227b554..8702f97 100644
--- a/docs/_modules/speechmatics/models.html
+++ b/docs/_modules/speechmatics/models.html
@@ -47,13 +47,13 @@ Source code for speechmatics.models
[docs]@dataclass
class FetchData:
- """Batch: Optional configuration for fetching file for transcription."""
+ """Batch: Optional configuration for fetching file for transcription."""
url: str
- """URL to fetch"""
+ """URL to fetch"""
auth_headers: str = None
- """
+ """
A list of additional headers to be added to the input fetch request
when using http or https. This is intended to support authentication or
authorization, for example by supplying an OAuth2 bearer token
@@ -62,23 +62,23 @@ Source code for speechmatics.models
[docs]@dataclass
class NotificationConfig:
- """Batch: Optional configuration for callback notification."""
+ """Batch: Optional configuration for callback notification."""
url: str
- """URL for notification. The `id` and `status` query parameters will be added."""
+ """URL for notification. The `id` and `status` query parameters will be added."""
contents: str = None
- """
+ """
Specifies a list of items to be attached to the notification message.
When multiple items are requested, they are included as named file
attachments.
"""
method: str = "post"
- """The HTTP(S) method to be used. Only `post` and `put` are supported."""
+ """The HTTP(S) method to be used. Only `post` and `put` are supported."""
auth_headers: str = None
- """
+ """
A list of additional headers to be added to the notification request
when using http or https. This is intended to support authentication or
authorization, for example by supplying an OAuth2 bearer token
@@ -87,21 +87,21 @@ Source code for speechmatics.models
[docs]@dataclass
class SRTOverrides:
- """Batch: Optional configuration for SRT output."""
+ """Batch: Optional configuration for SRT output."""
max_line_length: int = 37
- """Maximum count of characters per subtitle line including white space"""
+ """Maximum count of characters per subtitle line including white space"""
max_lines: int = 2
- """Sets maximum count of lines in a subtitle section"""
+ """Sets maximum count of lines in a subtitle section"""
[docs]@dataclass
class _TranscriptionConfig: # pylint: disable=too-many-instance-attributes
- """Base model for defining transcription parameters."""
+ """Base model for defining transcription parameters."""
def __init__(self, language=None, **kwargs):
- """
+ """
Ignores values which are not dataclass members when initalising.
This allows **kwargs to contain fields which are not in the model,
which is useful for reusing code to build RT and batch configs.
@@ -119,114 +119,130 @@ Source code for speechmatics.models
setattr(self, key, value)
[docs] def asdict(self) -> Dict[Any, Any]:
- """Returns model as a dict while excluding None values recursively."""
+ """Returns model as a dict while excluding None values recursively."""
return asdict(
self, dict_factory=lambda x: {k: v for (k, v) in x if v is not None}
)
language: str = "en"
- """ISO 639-1 language code. eg. `en`"""
+ """ISO 639-1 language code. eg. `en`"""
operating_point: str = None
- """Specifies which acoustic model to use."""
+ """Specifies which acoustic model to use."""
output_locale: str = None
- """RFC-5646 language code for transcript output. eg. `en-AU`"""
+ """RFC-5646 language code for transcript output. eg. `en-AU`"""
diarization: str = None
- """Indicates type of diarization to use, if any."""
+ """Indicates type of diarization to use, if any."""
additional_vocab: dict = None
- """Additional vocabulary that is not part of the standard language."""
+ """Additional vocabulary that is not part of the standard language."""
punctuation_overrides: dict = None
- """Permitted puctuation marks for advanced punctuation."""
+ """Permitted puctuation marks for advanced punctuation."""
domain: str = None
- """Optionally request a language pack optimized for a specific domain,
+ """Optionally request a language pack optimized for a specific domain,
e.g. 'finance'"""
enable_entities: bool = None
- """Indicates if inverse text normalization entity output is enabled."""
+ """Indicates if inverse text normalization entity output is enabled."""
[docs]@dataclass
class RTSpeakerDiarizationConfig:
- """Real-time mode: Speaker diarization config."""
+ """Real-time mode: Speaker diarization config."""
max_speakers: int = None
- """This enforces the maximum number of speakers allowed in a single audio stream."""
+ """This enforces the maximum number of speakers allowed in a single audio stream."""
[docs]@dataclass
class BatchSpeakerDiarizationConfig:
- """Batch mode: Speaker diarization config."""
+ """Batch mode: Speaker diarization config."""
- speaker_sensitivity: int = None
- """The sensitivity of the speaker detection."""
+ speaker_sensitivity: float = None
+ """The sensitivity of the speaker detection.
+ This is a number between 0 and 1, where 0 means least sensitive and 1 means
+ most sensitive."""
[docs]@dataclass
class BatchTranslationConfig:
- """Batch mode: Translation config."""
+ """Batch mode: Translation config."""
target_languages: List[str] = None
- """Target languages for which translation should be produced"""
+ """Target languages for which translation should be produced"""
+
+
+[docs]@dataclass
+class BatchLanguageIdentificationConfig:
+ """Batch mode: Language identification config."""
+
+ expected_languages: List[str] = None
+ """Expected languages for language identification"""
[docs]@dataclass(init=False)
class TranscriptionConfig(_TranscriptionConfig):
- """Real-time: Defines transcription parameters."""
+ """Real-time: Defines transcription parameters."""
max_delay: float = None
- """Maximum acceptable delay."""
+ """Maximum acceptable delay."""
max_delay_mode: str = None
- """Determines whether the threshold specified in max_delay can be exceeded
+ """Determines whether the threshold specified in max_delay can be exceeded
if a potential entity is detected. Flexible means if a potential entity
is detected, then the max_delay can be overriden until the end of that
entity. Fixed means that max_delay specified ignores any potential
entity that would not be completed within that threshold."""
speaker_diarization_config: RTSpeakerDiarizationConfig = None
- """Configuration for speaker diarization."""
+ """Configuration for speaker diarization."""
speaker_change_sensitivity: float = None
- """Sensitivity level for speaker change."""
+ """Sensitivity level for speaker change."""
enable_partials: bool = None
- """Indicates if partial transcription, where words are produced
+ """Indicates if partial transcription, where words are produced
immediately, is enabled. """
[docs]@dataclass(init=False)
class BatchTranscriptionConfig(_TranscriptionConfig):
- """Batch: Defines transcription parameters for batch requests.
+ """Batch: Defines transcription parameters for batch requests.
The `.as_config()` method will return it wrapped into a Speechmatics json config."""
fetch_data: FetchData = None
- """Optional configuration for fetching file for transcription."""
+ """Optional configuration for fetching file for transcription."""
notification_config: NotificationConfig = None
- """Optional configuration for callback notification."""
+ """Optional configuration for callback notification."""
+
+ language_identification_config: BatchLanguageIdentificationConfig = None
+ """Optional configuration for language identification."""
translation_config: BatchTranslationConfig = None
- """Optional configuration for translation."""
+ """Optional configuration for translation."""
srt_overrides: SRTOverrides = None
- """Optional configuration for SRT output."""
+ """Optional configuration for SRT output."""
speaker_diarization_config: BatchSpeakerDiarizationConfig = None
- """The sensitivity of the speaker detection."""
+ """The sensitivity of the speaker detection."""
channel_diarization_labels: List[str] = None
- """Add your own speaker or channel labels to the transcript"""
+ """Add your own speaker or channel labels to the transcript"""
def as_config(self):
dictionary = self.asdict()
fetch_data = dictionary.pop("fetch_data", None)
notification_config = dictionary.pop("notification_config", None)
+ language_identification_config = dictionary.pop(
+ "language_identification_config", None
+ )
translation_config = dictionary.pop("translation_config", None)
srt_overrides = dictionary.pop("srt_overrides", None)
@@ -240,6 +256,9 @@ Source code for speechmatics.models
notification_config = [notification_config]
config["notification_config"] = notification_config
+ if language_identification_config:
+ config["language_identification_config"] = language_identification_config
+
if translation_config:
config["translation_config"] = translation_config
@@ -251,17 +270,17 @@ Source code for speechmatics.models
[docs]@dataclass
class AudioSettings:
- """Real-time: Defines audio parameters."""
+ """Real-time: Defines audio parameters."""
encoding: str = None
- """Encoding format when raw audio is used. Allowed values are
+ """Encoding format when raw audio is used. Allowed values are
`pcm_f32le`, `pcm_s16le` and `mulaw`."""
sample_rate: int = 44100
- """Sampling rate in hertz."""
+ """Sampling rate in hertz."""
chunk_size: int = 1024 * 4
- """Chunk size."""
+ """Chunk size."""
def asdict(self):
if not self.encoding:
@@ -276,83 +295,83 @@ Source code for speechmatics.models
[docs]@dataclass
class ConnectionSettings:
- """Defines connection parameters."""
+ """Defines connection parameters."""
url: str
- """Websocket server endpoint."""
+ """Websocket server endpoint."""
message_buffer_size: int = 512
- """Message buffer size in bytes."""
+ """Message buffer size in bytes."""
ssl_context: ssl.SSLContext = field(default_factory=ssl.create_default_context)
- """SSL context."""
+ """SSL context."""
semaphore_timeout_seconds: float = 120
- """Semaphore timeout in seconds."""
+ """Semaphore timeout in seconds."""
ping_timeout_seconds: float = 60
- """Ping-pong timeout in seconds."""
+ """Ping-pong timeout in seconds."""
auth_token: str = None
- """auth token to authenticate a customer.
+ """auth token to authenticate a customer.
This auth token is only applicable for RT-SaaS."""
generate_temp_token: Optional[bool] = False
- """Automatically generate a temporary token for authentication.
+ """Automatically generate a temporary token for authentication.
Non-enterprise customers must set this to True. Enterprise customers should set this to False."""
[docs]class ClientMessageType(str, Enum):
# pylint: disable=invalid-name
- """Real-time: Defines various messages sent from client to server."""
+ """Real-time: Defines various messages sent from client to server."""
StartRecognition = "StartRecognition"
- """Initiates a recognition job based on configuration set previously."""
+ """Initiates a recognition job based on configuration set previously."""
AddAudio = "AddAudio"
- """Adds more audio data to the recognition job. The server confirms
+ """Adds more audio data to the recognition job. The server confirms
receipt by sending an :py:attr:`ServerMessageType.AudioAdded` message."""
EndOfStream = "EndOfStream"
- """Indicates that the client has no more audio to send."""
+ """Indicates that the client has no more audio to send."""
SetRecognitionConfig = "SetRecognitionConfig"
- """Allows the client to re-configure the recognition session."""
+ """Allows the client to re-configure the recognition session."""
[docs]class ServerMessageType(str, Enum):
# pylint: disable=invalid-name
- """Real-time: Defines various message types sent from server to client."""
+ """Real-time: Defines various message types sent from server to client."""
RecognitionStarted = "RecognitionStarted"
- """Server response to :py:attr:`ClientMessageType.StartRecognition`,
+ """Server response to :py:attr:`ClientMessageType.StartRecognition`,
acknowledging that a recognition session has started."""
AudioAdded = "AudioAdded"
- """Server response to :py:attr:`ClientMessageType.AddAudio`, indicating
+ """Server response to :py:attr:`ClientMessageType.AddAudio`, indicating
that audio has been added successfully."""
AddPartialTranscript = "AddPartialTranscript"
- """Indicates a partial transcript, which is an incomplete transcript that
+ """Indicates a partial transcript, which is an incomplete transcript that
is immediately produced and may change as more context becomes available.
"""
AddTranscript = "AddTranscript"
- """Indicates the final transcript of a part of the audio."""
+ """Indicates the final transcript of a part of the audio."""
EndOfTranscript = "EndOfTranscript"
- """Server response to :py:attr:`ClientMessageType.EndOfStream`,
+ """Server response to :py:attr:`ClientMessageType.EndOfStream`,
after the server has finished sending all :py:attr:`AddTranscript`
messages."""
Info = "Info"
- """Indicates a generic info message."""
+ """Indicates a generic info message."""
Warning = "Warning"
- """Indicates a generic warning message."""
+ """Indicates a generic warning message."""
Error = "Error"
- """Indicates n generic error message."""
+ """Indicates n generic error message."""
@@ -431,7 +450,7 @@ Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
diff --git a/docs/_static/alabaster.css b/docs/_static/alabaster.css
index 6476cd5..461b3ed 100644
--- a/docs/_static/alabaster.css
+++ b/docs/_static/alabaster.css
@@ -419,9 +419,7 @@ table.footnote td {
}
dl {
- margin-left: 0;
- margin-right: 0;
- margin-top: 0;
+ margin: 0;
padding: 0;
}
diff --git a/docs/batch_client.html b/docs/batch_client.html
index 4472e05..d1fa45f 100644
--- a/docs/batch_client.html
+++ b/docs/batch_client.html
@@ -314,7 +314,7 @@ Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
|
Sub-commands¶
Transcribe an audio file or stream in real time and output the results to the console.
speechmatics rt transcribe [-h] [--enable-partials] [--punctuation-sensitivity PUNCTUATION_SENSITIVITY] [--speaker-diarization-max-speakers SPEAKER_DIARIZATION_MAX_SPEAKERS]
- [--speaker-change-sensitivity SPEAKER_CHANGE_SENSITIVITY] [--speaker-change-token] [--max-delay MAX_DELAY] [--max-delay-mode {fixed,flexible}]
- [--raw ENCODING] [--sample-rate SAMPLE_RATE] [--chunk-size CHUNK_SIZE] [--buffer-size BUFFER_SIZE] [--print-json]
- [--diarization {none,speaker,speaker_change}] [--url URL] [--auth-token AUTH_TOKEN] [--ssl-mode {regular,insecure,none}] [--generate-temp-token]
- [--config-file CONFIG_FILE] [--lang LANGUAGE] [--operating-point {standard,enhanced}] [--domain DOMAIN] [--output-locale LOCALE]
- [--additional-vocab [ADDITIONAL_VOCAB [ADDITIONAL_VOCAB ...]]] [--additional-vocab-file VOCAB_FILEPATH]
- [--punctuation-permitted-marks PUNCTUATION_PERMITTED_MARKS] [--enable-entities] [--translation-langs TRANSLATION_TARGET_LANGUAGES]
+ [--speaker-change-sensitivity SPEAKER_CHANGE_SENSITIVITY] [--speaker-change-token] [--max-delay MAX_DELAY] [--max-delay-mode {fixed,flexible}] [--raw ENCODING]
+ [--sample-rate SAMPLE_RATE] [--chunk-size CHUNK_SIZE] [--buffer-size BUFFER_SIZE] [--print-json] [--diarization {none,speaker,speaker_change}] [--url URL]
+ [--auth-token AUTH_TOKEN] [--ssl-mode {regular,insecure,none}] [--generate-temp-token] [--config-file CONFIG_FILE] [--lang LANGUAGE] [--operating-point {standard,enhanced}]
+ [--domain DOMAIN] [--output-locale LOCALE] [--additional-vocab [ADDITIONAL_VOCAB [ADDITIONAL_VOCAB ...]]] [--additional-vocab-file VOCAB_FILEPATH]
+ [--punctuation-permitted-marks PUNCTUATION_PERMITTED_MARKS] [--enable-entities] [--translation-target-langs TRANSLATION_TARGET_LANGUAGES]
FILEPATHS [FILEPATHS ...]
@@ -193,7 +192,7 @@ Named Argumentsspeechmatics batch transcribe [-h] [--url URL] [--auth-token AUTH_TOKEN] [--ssl-mode {regular,insecure,none}] [--generate-temp-token] [--config-file CONFIG_FILE] [--lang LANGUAGE]
[--operating-point {standard,enhanced}] [--domain DOMAIN] [--output-locale LOCALE] [--additional-vocab [ADDITIONAL_VOCAB [ADDITIONAL_VOCAB ...]]]
[--additional-vocab-file VOCAB_FILEPATH] [--punctuation-permitted-marks PUNCTUATION_PERMITTED_MARKS] [--enable-entities]
- [--translation-langs TRANSLATION_TARGET_LANGUAGES] [--output-format {txt,json,json-v2,srt}]
- [--speaker-diarization-sensitivity SPEAKER_DIARIZATION_SENSITIVITY] [--diarization {none,speaker,channel,channel_and_speaker_change}]
- [--channel-diarization-labels CHANNEL_DIARIZATION_LABELS [CHANNEL_DIARIZATION_LABELS ...]]
+ [--translation-target-langs TRANSLATION_TARGET_LANGUAGES] [--output-format {txt,json,json-v2,srt}] [--speaker-diarization-sensitivity SPEAKER_DIARIZATION_SENSITIVITY]
+ [--diarization {none,speaker,channel,channel_and_speaker_change}] [--channel-diarization-labels CHANNEL_DIARIZATION_LABELS [CHANNEL_DIARIZATION_LABELS ...]]
FILEPATHS [FILEPATHS ...]
@@ -283,7 +281,7 @@ Named Argumentsspeechmatics batch submit [-h] [--url URL] [--auth-token AUTH_TOKEN] [--ssl-mode {regular,insecure,none}] [--generate-temp-token] [--config-file CONFIG_FILE] [--lang LANGUAGE]
[--operating-point {standard,enhanced}] [--domain DOMAIN] [--output-locale LOCALE] [--additional-vocab [ADDITIONAL_VOCAB [ADDITIONAL_VOCAB ...]]]
- [--additional-vocab-file VOCAB_FILEPATH] [--punctuation-permitted-marks PUNCTUATION_PERMITTED_MARKS] [--enable-entities]
- [--translation-langs TRANSLATION_TARGET_LANGUAGES] [--output-format {txt,json,json-v2,srt}]
- [--speaker-diarization-sensitivity SPEAKER_DIARIZATION_SENSITIVITY] [--diarization {none,speaker,channel,channel_and_speaker_change}]
+ [--additional-vocab-file VOCAB_FILEPATH] [--punctuation-permitted-marks PUNCTUATION_PERMITTED_MARKS] [--enable-entities] [--translation-target-langs TRANSLATION_TARGET_LANGUAGES]
+ [--output-format {txt,json,json-v2,srt}] [--speaker-diarization-sensitivity SPEAKER_DIARIZATION_SENSITIVITY] [--diarization {none,speaker,channel,channel_and_speaker_change}]
[--channel-diarization-labels CHANNEL_DIARIZATION_LABELS [CHANNEL_DIARIZATION_LABELS ...]]
FILEPATHS [FILEPATHS ...]
@@ -370,7 +367,7 @@ Named Arguments
get-results¶
Retrieve results of a transcription job.
-speechmatics batch get-results [-h] [--url URL] [--auth-token AUTH_TOKEN] [--ssl-mode {regular,insecure,none}] [--generate-temp-token] [--output-format {txt,json,json-v2,srt}]
- --job-id JOB_ID
+speechmatics batch get-results [-h] [--url URL] [--auth-token AUTH_TOKEN] [--ssl-mode {regular,insecure,none}] [--generate-temp-token] [--output-format {txt,json,json-v2,srt}] --job-id JOB_ID
@@ -455,8 +451,7 @@ Named Arguments
delete¶
Delete the results of a transcription job.
-speechmatics batch delete [-h] [--url URL] [--auth-token AUTH_TOKEN] [--ssl-mode {regular,insecure,none}] [--generate-temp-token] [--output-format {txt,json,json-v2,srt}] --job-id
- JOB_ID [--force]
+speechmatics batch delete [-h] [--url URL] [--auth-token AUTH_TOKEN] [--ssl-mode {regular,insecure,none}] [--generate-temp-token] [--output-format {txt,json,json-v2,srt}] --job-id JOB_ID [--force]
@@ -526,12 +521,11 @@ Named Arguments¶
Real-time commands. RETAINED FOR LEGACY COMPATIBILITY.
speechmatics transcribe [-h] [--enable-partials] [--punctuation-sensitivity PUNCTUATION_SENSITIVITY] [--speaker-diarization-max-speakers SPEAKER_DIARIZATION_MAX_SPEAKERS]
- [--speaker-change-sensitivity SPEAKER_CHANGE_SENSITIVITY] [--speaker-change-token] [--max-delay MAX_DELAY] [--max-delay-mode {fixed,flexible}]
- [--raw ENCODING] [--sample-rate SAMPLE_RATE] [--chunk-size CHUNK_SIZE] [--buffer-size BUFFER_SIZE] [--print-json]
- [--diarization {none,speaker,speaker_change}] [--url URL] [--auth-token AUTH_TOKEN] [--ssl-mode {regular,insecure,none}] [--generate-temp-token]
- [--config-file CONFIG_FILE] [--lang LANGUAGE] [--operating-point {standard,enhanced}] [--domain DOMAIN] [--output-locale LOCALE]
- [--additional-vocab [ADDITIONAL_VOCAB [ADDITIONAL_VOCAB ...]]] [--additional-vocab-file VOCAB_FILEPATH]
- [--punctuation-permitted-marks PUNCTUATION_PERMITTED_MARKS] [--enable-entities] [--translation-langs TRANSLATION_TARGET_LANGUAGES]
+ [--speaker-change-sensitivity SPEAKER_CHANGE_SENSITIVITY] [--speaker-change-token] [--max-delay MAX_DELAY] [--max-delay-mode {fixed,flexible}] [--raw ENCODING]
+ [--sample-rate SAMPLE_RATE] [--chunk-size CHUNK_SIZE] [--buffer-size BUFFER_SIZE] [--print-json] [--diarization {none,speaker,speaker_change}] [--url URL] [--auth-token AUTH_TOKEN]
+ [--ssl-mode {regular,insecure,none}] [--generate-temp-token] [--config-file CONFIG_FILE] [--lang LANGUAGE] [--operating-point {standard,enhanced}] [--domain DOMAIN]
+ [--output-locale LOCALE] [--additional-vocab [ADDITIONAL_VOCAB [ADDITIONAL_VOCAB ...]]] [--additional-vocab-file VOCAB_FILEPATH]
+ [--punctuation-permitted-marks PUNCTUATION_PERMITTED_MARKS] [--enable-entities] [--translation-target-langs TRANSLATION_TARGET_LANGUAGES]
FILEPATHS [FILEPATHS ...]
@@ -637,7 +631,7 @@ Named ArgumentsQuick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
|
Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
|
Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
|
Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
|
B
BATCH_SELF_SERVICE_URL (in module speechmatics.constants)
BatchClient (class in speechmatics.batch_client)
+
+ BatchLanguageIdentificationConfig (class in speechmatics.models)
@@ -165,15 +167,17 @@ E
- encoding (speechmatics.models.AudioSettings attribute)
-
L
Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
diff --git a/docs/helpers.html b/docs/helpers.html
index 74a7a19..fb983b3 100644
--- a/docs/helpers.html
+++ b/docs/helpers.html
@@ -163,7 +163,7 @@ Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
|
Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
|
+
+-
+class speechmatics.models.BatchLanguageIdentificationConfig(expected_languages: Optional[List[str]] = None)[source]¶
+Batch mode: Language identification config.
+
+-
+expected_languages: List[str] = None¶
+Expected languages for language identification
+
+
+
+
-
-class speechmatics.models.BatchSpeakerDiarizationConfig(speaker_sensitivity: Optional[int] = None)[source]¶
+class speechmatics.models.BatchSpeakerDiarizationConfig(speaker_sensitivity: Optional[float] = None)[source]¶
Batch mode: Speaker diarization config.
@@ -151,6 +165,12 @@
Optional configuration for fetching file for transcription.
+-
+language_identification_config: speechmatics.models.BatchLanguageIdentificationConfig = None¶
+Optional configuration for language identification.
+
+
-
notification_config: speechmatics.models.NotificationConfig = None¶
@@ -533,7 +553,7 @@ Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
|
Quick search
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
diff --git a/docs/search.html b/docs/search.html
index 7c6cc64..280e04d 100644
--- a/docs/search.html
+++ b/docs/search.html
@@ -131,7 +131,7 @@ Related Topics
|
Powered by Sphinx 4.4.0
- & Alabaster 0.7.13
+ & Alabaster 0.7.12
diff --git a/docs/searchindex.js b/docs/searchindex.js
index e6895e3..8efc16b 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["batch_client","cli_parser","client","constants","exceptions","helpers","index","models"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":4,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,"sphinx.ext.viewcode":1,sphinx:56},filenames:["batch_client.rst","cli_parser.rst","client.rst","constants.rst","exceptions.rst","helpers.rst","index.rst","models.rst"],objects:{"speechmatics.batch_client":[[0,1,1,"","BatchClient"]],"speechmatics.batch_client.BatchClient":[[0,2,1,"","check_job_status"],[0,2,1,"","close"],[0,2,1,"","connect"],[0,2,1,"","delete_job"],[0,2,1,"","get_job_result"],[0,2,1,"","list_jobs"],[0,2,1,"","send_request"],[0,2,1,"","submit_job"],[0,2,1,"","wait_for_completion"]],"speechmatics.client":[[2,1,1,"","WebsocketClient"]],"speechmatics.client.WebsocketClient":[[2,2,1,"","add_event_handler"],[2,2,1,"","add_middleware"],[2,2,1,"","get_language_pack_info"],[2,2,1,"","run"],[2,2,1,"","run_synchronously"],[2,2,1,"","stop"],[2,2,1,"","update_transcription_config"]],"speechmatics.constants":[[3,3,1,"","BATCH_SELF_SERVICE_URL"],[3,3,1,"","RT_SELF_SERVICE_URL"]],"speechmatics.exceptions":[[4,4,1,"","EndOfTranscriptException"],[4,4,1,"","ForceEndSession"],[4,4,1,"","JobNotFoundException"],[4,4,1,"","TranscriptionError"]],"speechmatics.helpers":[[5,5,1,"","del_none"],[5,5,1,"","json_utf8"],[5,5,1,"","read_in_chunks"]],"speechmatics.models":[[7,1,1,"","AudioSettings"],[7,1,1,"","BatchSpeakerDiarizationConfig"],[7,1,1,"","BatchTranscriptionConfig"],[7,1,1,"","BatchTranslationConfig"],[7,1,1,"","ClientMessageType"],[7,1,1,"","ConnectionSettings"],[7,1,1,"","FetchData"],[7,1,1,"","NotificationConfig"],[7,1,1,"","RTSpeakerDiarizationConfig"],[7,1,1,"","SRTOverrides"],[7,1,1,"","ServerMessageType"],[7,1,1,"","TranscriptionConfig"],[7,1,1,"","_TranscriptionConfig"]],"speechmatics.models.AudioSettings":[[7,6,1,"","chunk_size"],[7,6,1,"","encoding"],[7,6,1,"","sample_rate"]],"speechmatics.models.BatchSpeakerDiarizationConfig":[[7,6,1,"","speaker_sensitivity"]],"speechmatics.models.BatchTranscriptionConfig":[[7,6,1,"","channel_diarization_labels"],[7,6,1,"","fetch_data"],[7,6,1,"","notification_config"],[7,6,1,"","speaker_diarization_config"],[7,6,1,"","srt_overrides"],[7,6,1,"","translation_config"]],"speechmatics.models.BatchTranslationConfig":[[7,6,1,"","target_languages"]],"speechmatics.models.ClientMessageType":[[7,6,1,"","AddAudio"],[7,6,1,"","EndOfStream"],[7,6,1,"","SetRecognitionConfig"],[7,6,1,"","StartRecognition"]],"speechmatics.models.ConnectionSettings":[[7,6,1,"","auth_token"],[7,6,1,"","generate_temp_token"],[7,6,1,"","message_buffer_size"],[7,6,1,"","ping_timeout_seconds"],[7,6,1,"","semaphore_timeout_seconds"],[7,6,1,"","ssl_context"],[7,6,1,"","url"]],"speechmatics.models.FetchData":[[7,6,1,"","auth_headers"],[7,6,1,"","url"]],"speechmatics.models.NotificationConfig":[[7,6,1,"","auth_headers"],[7,6,1,"","contents"],[7,6,1,"","method"],[7,6,1,"","url"]],"speechmatics.models.RTSpeakerDiarizationConfig":[[7,6,1,"","max_speakers"]],"speechmatics.models.SRTOverrides":[[7,6,1,"","max_line_length"],[7,6,1,"","max_lines"]],"speechmatics.models.ServerMessageType":[[7,6,1,"","AddPartialTranscript"],[7,6,1,"","AddTranscript"],[7,6,1,"","AudioAdded"],[7,6,1,"","EndOfTranscript"],[7,6,1,"","Error"],[7,6,1,"","Info"],[7,6,1,"","RecognitionStarted"],[7,6,1,"","Warning"]],"speechmatics.models.TranscriptionConfig":[[7,6,1,"","enable_partials"],[7,6,1,"","max_delay"],[7,6,1,"","max_delay_mode"],[7,6,1,"","speaker_change_sensitivity"],[7,6,1,"","speaker_diarization_config"]],"speechmatics.models._TranscriptionConfig":[[7,6,1,"","additional_vocab"],[7,2,1,"","asdict"],[7,6,1,"","diarization"],[7,6,1,"","domain"],[7,6,1,"","enable_entities"],[7,6,1,"","language"],[7,6,1,"","operating_point"],[7,6,1,"","output_locale"],[7,6,1,"","punctuation_overrides"]],speechmatics:[[0,0,0,"-","batch_client"],[2,0,0,"-","client"],[3,0,0,"-","constants"],[4,0,0,"-","exceptions"],[5,0,0,"-","helpers"],[7,0,0,"-","models"]]},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","data","Python data"],"4":["py","exception","Python exception"],"5":["py","function","Python function"],"6":["py","attribute","Python attribute"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:data","4":"py:exception","5":"py:function","6":"py:attribute"},terms:{"0":1,"1":[1,7],"100":[0,1],"12":1,"120":7,"168":1,"192":1,"2":[1,7],"20":1,"37":7,"404":0,"4096":[1,7],"44100":[1,7],"5":1,"512":[1,7],"5646":7,"60":7,"639":[1,7],"7":[0,1],"8":1,"9000":[1,2],"boolean":2,"byte":[0,1,5,7],"class":[0,1,2,7],"default":[0,1],"final":[1,7],"float":7,"function":[2,5],"import":6,"int":[5,7],"new":2,"return":[0,1,2,5,7],"true":[0,1,6,7],"while":[1,7],A:[2,5,7],FOR:1,For:[0,2],If:[1,2],It:0,The:[1,2,3,6,7],With:1,_transcriptionconfig:7,about:1,accept:[0,1,7],access:6,accur:1,acknowledg:7,acoust:[1,7],ad:[2,3,7],add:[1,2,6,7],add_event_handl:[2,6],add_middlewar:2,addaudio:[2,7],addit:[1,7],additional_vocab:[1,7],addpartialtranscript:[6,7],addtranscript:[2,6,7],advanc:[1,7],after:7,afterward:0,alia:0,all:[0,1,2,5,7],allow:[1,7],also:0,alter:2,an:[0,1,2,4,6,7],ani:[0,2,7],anymor:1,api:[0,1,2,3,6],appli:1,applianc:[0,1],applic:7,ar:[0,1,2,5,7],arg:2,argument:[2,6],as_config:7,asdict:7,asr:[0,1,2,3],associ:0,async:[2,5],asynchron:2,asyncio:2,asynciter:5,attach:7,au:7,audio:[0,1,2,5,6,7],audio_file_path:6,audio_set:2,audioad:7,audioset:[2,6,7],auth:[1,7],auth_head:7,auth_token:[0,1,6,7],authent:[1,7],author:[1,7],automat:[1,7],avail:[3,7],base:[2,7],batch:[0,3,6,7],batch_client:6,batch_self_service_url:3,batchclient:0,batchspeakerdiarizationconfig:7,batchtranscriptionconfig:[0,7],batchtranslationconfig:7,bearer:7,becom:7,been:[2,7],befor:1,begin:2,being:[2,6],below:6,best:2,binari:2,block:[0,2],bool:[0,2,7],buffer:[1,7],buffer_s:1,call:2,callabl:2,callback:[2,7],caller:2,can:[1,2,4,7],cancel:0,certif:1,chang:[1,5,7],channel:[1,7],channel_and_speaker_chang:1,channel_diarization_label:[1,7],charact:7,check:0,check_job_statu:0,choic:1,chunk:[1,5,7],chunk_siz:[1,5,7],clean:0,cli:6,client:[0,1,6,7],clientmessagetyp:7,close:0,code:[1,7],collect:5,com:[1,3,6],comma:1,compat:1,complet:[0,7],computation:1,conf:6,config:[0,2,7],config_fil:1,configur:[0,1,2,7],confirm:7,conjunct:2,connect:[0,2,7],connection_set:[0,2],connection_url:6,connectionset:[0,2,6,7],consol:1,constant:3,consum:2,content:[1,7],context:[0,1,7],copi:2,count:7,creat:[0,1,6],custom:[1,3,6,7],dai:[0,1],data:[1,2,5,7],de:1,debug:1,decor:5,def:6,defin:[6,7],del_non:5,delai:[1,7],delet:[0,5],delete_job:0,detect:[1,7],determin:7,diariz:[1,7],dict:[0,2,5,7],dictionari:5,directli:0,doc:2,doe:0,doesn:3,domain:[1,7],don:[2,6],e:[0,1,2,7],each:[1,5],earli:4,eg:[1,7],en:[1,2,6,7],enabl:[1,7],enable_ent:7,enable_parti:[6,7],encod:[1,7],encodingof:1,end:[2,3,4,7],endofstream:7,endoftranscript:7,endoftranscriptexcept:4,endpoint:[0,7],enforc:[1,7],enhanc:1,enterpris:[1,3,6,7],entiti:[1,7],entri:5,environ:1,error:[0,4,7],eu2:[3,6],event:[2,4,6],event_handl:[2,6],event_nam:[2,6],everi:2,exampl:[1,2,7],exceed:[2,7],except:[0,2,6],exclud:7,exist:0,expect:1,expens:1,expos:2,f:6,factori:7,fail:0,fals:[0,1,7],fetch:7,fetch_data:7,fetchdata:7,field:2,file:[0,1,2,5,6,7],filenam:0,filepath:1,financ:[1,7],finish:[2,4,7],first:2,fix:[1,7],flag:1,flexibl:[1,7],foracknowledg:1,forc:[0,1,4],forceendsess:4,forcefulli:2,format:[0,1,7],found:[0,4],fr:1,from:[1,2,4,5,7],full:6,func:5,g:[0,1,7],gener:[1,7],generate_temp_token:[1,6,7],get:2,get_job_result:0,get_language_pack_info:2,github:6,given:2,global:1,gnocchi:1,h:1,ha:[2,4,7],handl:[0,1,2],handler:[2,4,6],have:3,header:7,helper:6,here:6,hertz:7,how:1,html:2,http:[0,1,2,3,7],httperror:0,httpx:0,hz:1,i:2,id:[0,1,4,7],ignor:7,illustr:6,immedi:7,impli:2,includ:[2,7],incom:2,incomplet:7,increas:1,index:6,indic:[1,2,4,7],info:[1,7],inform:[1,2],initi:7,input:[1,5,7],insecur:1,instanti:2,intend:7,interact:2,interfac:[0,2],interpret:1,inth:1,invalid:0,invers:7,io:[2,5],iobas:[2,5],iso:[1,7],item:7,job:[0,4,7],job_id:[0,1],jobnotfoundexcept:[0,4],json:[0,1,5,7],json_utf8:5,just:2,kwarg:[0,2,7],label1:1,label2:1,label:[1,7],lambda:2,lang:1,languag:[1,2,3,6,7],language_pack_info:2,larger:1,last:[0,1],latenc:1,later:1,latest:2,legaci:1,length:5,level:[1,7],librari:[0,2,3,4,5,7],like:[1,2,5],line:[1,7],list:[0,2,7],list_job:0,list_of_job:0,local:1,localhost:2,log:1,mai:[0,2,7],manag:[0,2],manifest:2,mark:[1,7],max:1,max_delai:[1,7],max_delay_mod:7,max_lin:7,max_line_length:7,max_sample_s:5,max_speak:7,maximum:[1,5,7],mean:7,messag:[1,2,7],message_buffer_s:7,metadata:6,method:[0,5,7],middl:1,middlewar:[2,4],min:1,mode:[6,7],model:[0,1,2,6],modul:6,more:[1,7],most:2,msg:[2,6],much:1,mulaw:7,multipl:[5,7],must:[0,1,7],n:7,name:[2,6,7],need:[2,6],new_transcription_config:2,nochi:1,nokei:1,non:[1,3,7],none:[0,1,2,5,7],normal:7,note:3,notif:7,notification_config:7,notificationconfig:7,number:[1,7],oauth2:7,object:[0,2,5],one:1,onli:[1,2,7],open:[0,6],oper:1,operating_point:7,optim:7,option:[0,1,7],order:4,os:0,other:[0,1],out:2,outgo:2,output:[1,5,7],output_local:7,overhead:1,overrid:1,overriden:7,own:[1,7],pack:[1,2,7],page:6,paramet:[0,2,5,6,7],part:[6,7],partial:[1,6,7],particular:2,pass:[0,2],path:[0,6],pathlik:0,pcm_f32le:[1,7],pcm_s16le:7,per:7,permit:[1,7],piec:1,ping:7,ping_timeout_second:7,place:5,plaintext:1,pleas:6,point:1,pong:7,pool:0,possibl:[1,2],post:7,potenti:7,pre:1,prefer:2,preset:1,previous:[0,7],print:[1,2,6],print_partial_transcript:6,print_transcript:6,probabl:2,process:[1,2],produc:[2,7],producer_consum:2,product:1,provid:[1,6],puctuat:7,punctuat:[1,7],punctuation_overrid:7,punctuation_permitted_mark:1,punctuation_sensit:1,put:7,queri:7,rais:[0,2,4,5],rate:[1,7],rather:1,raw:[1,7],rb:6,re:[2,7],read:[1,2,5],read_in_chunk:5,readm:6,readthedoc:2,real:[1,2,7],realtim:[3,6],receipt:7,receiv:[1,2],recognisedent:1,recognit:[2,7],recognitionstart:[2,7],recurs:[5,7],redirect:1,refer:2,regist:6,regular:1,remov:1,repres:1,request:[0,1,7],requir:[0,1],respect:1,respond:2,respons:[0,7],rest:0,result:[0,2],retain:1,retriev:1,rfc:7,rt:[3,6,7],rt_self_service_url:3,rtspeakerdiarizationconfig:7,run:[0,1,2],run_synchron:[2,6],s:[1,5,7],saa:[0,1,7],sampl:[1,7],sample_r:[1,7],sc:1,search:6,second:[2,7],section:7,see:6,select:1,self:[1,3],semaphor:7,semaphore_timeout_second:7,send:[0,1,7],send_request:0,sensit:[1,7],sent:[2,7],separ:1,sequenc:5,server:[1,2,7],servermessagetyp:[2,6,7],servic:3,session:[2,4,7],set:[0,2,6,7],setrecognitionconfig:[2,7],share:1,should:[1,2,7],show:1,sign:1,simpl:[1,2],singl:[1,7],size:[1,5,7],small:1,sound:1,sourc:[0,2,4,5,7],space:[1,7],speaker:[1,7],speaker_chang:1,speaker_change_sensit:[1,7],speaker_diarization_config:7,speaker_diarization_max_speak:1,speaker_diarization_sensit:1,speaker_sensit:7,special:1,specif:7,specifi:[1,7],speech:1,srt:[0,1,7],srt_overrid:7,srtoverrid:7,ssl:[1,7],ssl_context:7,sslcontext:7,standard:[1,7],start:7,startrecognit:7,statu:[0,7],stderr:1,stdout:1,still:0,stop:2,str:[0,2,7],stream:[1,2,5,7],sub:6,submit:0,submit_job:0,subset:2,subtitl:7,successfulli:7,suppli:7,support:7,symbol:1,synchron:2,t:[2,3,6],target:7,target_languag:7,task:2,temp:1,temporari:[1,7],termin:0,text:7,than:[0,1],thei:[2,7],thi:[0,1,2,5,6,7],threshold:7,time:[1,2,7],timeout:[2,7],timeouterror:2,token:[0,1,6,7],too:1,tool:6,transcrib:6,transcript:[0,1,2,4,6,7],transcription_config:[0,2],transcription_format:0,transcriptionconfig:[2,6,7],transcriptionerror:[0,4],translat:[1,7],translation_config:7,translation_target_languag:1,tupl:0,turn:5,txt:[0,1],type:[0,1,2,5,7],unbreak:1,union:0,unnecessari:1,unset:0,until:[0,2,7],up:0,updat:[1,2],update_transcription_config:2,url:[0,1,2,3,6,7],us:[0,1,2,3,4,5,7],usag:1,user:[2,4],util:5,v2:[0,1,2,3,6],v:1,valid:[0,1,2],valu:[1,5,7],valueerror:[2,5],variou:7,verbos:1,via:2,vocab:1,vocab_filepath:1,vocabulari:7,vv:1,wa:[1,4,5],wai:2,wait:1,wait_for_complet:0,warn:7,wav:6,waveform:6,we:[0,2],websocket:[1,2,7],websocketcli:[2,6],when:[0,1,2,7],where:[1,5,7],wherev:1,whether:[1,2,7],which:[0,1,2,5,7],white:7,wire:1,within:[0,1,7],word:7,work:1,would:7,wrap:7,wrapper:[0,2,6],ws:6,wss:[1,2,3,6],yet:2,yield:5,you:[0,1,2],your:[1,7]},titles:["speechmatics.batch_client","Speechmatics CLI Tool","speechmatics.client","speechmatics.client","speechmatics.exceptions","speechmatics.helpers","speechmatics-python","speechmatics.models"],titleterms:{argument:1,batch:1,batch_client:0,cli:1,client:[2,3],command:[1,6],config:1,delet:1,exampl:6,except:4,get:1,helper:5,indic:6,job:1,librari:6,line:6,list:1,mode:1,model:7,name:1,posit:1,python:6,refer:6,result:1,rt:1,set:1,speechmat:[0,1,2,3,4,5,6,7],statu:1,sub:1,submit:1,tabl:6,tool:1,transcrib:1,unset:1,usag:6}})
\ No newline at end of file
+Search.setIndex({docnames:["batch_client","cli_parser","client","constants","exceptions","helpers","index","models"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":4,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,"sphinx.ext.viewcode":1,sphinx:56},filenames:["batch_client.rst","cli_parser.rst","client.rst","constants.rst","exceptions.rst","helpers.rst","index.rst","models.rst"],objects:{"speechmatics.batch_client":[[0,1,1,"","BatchClient"]],"speechmatics.batch_client.BatchClient":[[0,2,1,"","check_job_status"],[0,2,1,"","close"],[0,2,1,"","connect"],[0,2,1,"","delete_job"],[0,2,1,"","get_job_result"],[0,2,1,"","list_jobs"],[0,2,1,"","send_request"],[0,2,1,"","submit_job"],[0,2,1,"","wait_for_completion"]],"speechmatics.client":[[2,1,1,"","WebsocketClient"]],"speechmatics.client.WebsocketClient":[[2,2,1,"","add_event_handler"],[2,2,1,"","add_middleware"],[2,2,1,"","get_language_pack_info"],[2,2,1,"","run"],[2,2,1,"","run_synchronously"],[2,2,1,"","stop"],[2,2,1,"","update_transcription_config"]],"speechmatics.constants":[[3,3,1,"","BATCH_SELF_SERVICE_URL"],[3,3,1,"","RT_SELF_SERVICE_URL"]],"speechmatics.exceptions":[[4,4,1,"","EndOfTranscriptException"],[4,4,1,"","ForceEndSession"],[4,4,1,"","JobNotFoundException"],[4,4,1,"","TranscriptionError"]],"speechmatics.helpers":[[5,5,1,"","del_none"],[5,5,1,"","json_utf8"],[5,5,1,"","read_in_chunks"]],"speechmatics.models":[[7,1,1,"","AudioSettings"],[7,1,1,"","BatchLanguageIdentificationConfig"],[7,1,1,"","BatchSpeakerDiarizationConfig"],[7,1,1,"","BatchTranscriptionConfig"],[7,1,1,"","BatchTranslationConfig"],[7,1,1,"","ClientMessageType"],[7,1,1,"","ConnectionSettings"],[7,1,1,"","FetchData"],[7,1,1,"","NotificationConfig"],[7,1,1,"","RTSpeakerDiarizationConfig"],[7,1,1,"","SRTOverrides"],[7,1,1,"","ServerMessageType"],[7,1,1,"","TranscriptionConfig"],[7,1,1,"","_TranscriptionConfig"]],"speechmatics.models.AudioSettings":[[7,6,1,"","chunk_size"],[7,6,1,"","encoding"],[7,6,1,"","sample_rate"]],"speechmatics.models.BatchLanguageIdentificationConfig":[[7,6,1,"","expected_languages"]],"speechmatics.models.BatchSpeakerDiarizationConfig":[[7,6,1,"","speaker_sensitivity"]],"speechmatics.models.BatchTranscriptionConfig":[[7,6,1,"","channel_diarization_labels"],[7,6,1,"","fetch_data"],[7,6,1,"","language_identification_config"],[7,6,1,"","notification_config"],[7,6,1,"","speaker_diarization_config"],[7,6,1,"","srt_overrides"],[7,6,1,"","translation_config"]],"speechmatics.models.BatchTranslationConfig":[[7,6,1,"","target_languages"]],"speechmatics.models.ClientMessageType":[[7,6,1,"","AddAudio"],[7,6,1,"","EndOfStream"],[7,6,1,"","SetRecognitionConfig"],[7,6,1,"","StartRecognition"]],"speechmatics.models.ConnectionSettings":[[7,6,1,"","auth_token"],[7,6,1,"","generate_temp_token"],[7,6,1,"","message_buffer_size"],[7,6,1,"","ping_timeout_seconds"],[7,6,1,"","semaphore_timeout_seconds"],[7,6,1,"","ssl_context"],[7,6,1,"","url"]],"speechmatics.models.FetchData":[[7,6,1,"","auth_headers"],[7,6,1,"","url"]],"speechmatics.models.NotificationConfig":[[7,6,1,"","auth_headers"],[7,6,1,"","contents"],[7,6,1,"","method"],[7,6,1,"","url"]],"speechmatics.models.RTSpeakerDiarizationConfig":[[7,6,1,"","max_speakers"]],"speechmatics.models.SRTOverrides":[[7,6,1,"","max_line_length"],[7,6,1,"","max_lines"]],"speechmatics.models.ServerMessageType":[[7,6,1,"","AddPartialTranscript"],[7,6,1,"","AddTranscript"],[7,6,1,"","AudioAdded"],[7,6,1,"","EndOfTranscript"],[7,6,1,"","Error"],[7,6,1,"","Info"],[7,6,1,"","RecognitionStarted"],[7,6,1,"","Warning"]],"speechmatics.models.TranscriptionConfig":[[7,6,1,"","enable_partials"],[7,6,1,"","max_delay"],[7,6,1,"","max_delay_mode"],[7,6,1,"","speaker_change_sensitivity"],[7,6,1,"","speaker_diarization_config"]],"speechmatics.models._TranscriptionConfig":[[7,6,1,"","additional_vocab"],[7,2,1,"","asdict"],[7,6,1,"","diarization"],[7,6,1,"","domain"],[7,6,1,"","enable_entities"],[7,6,1,"","language"],[7,6,1,"","operating_point"],[7,6,1,"","output_locale"],[7,6,1,"","punctuation_overrides"]],speechmatics:[[0,0,0,"-","batch_client"],[2,0,0,"-","client"],[3,0,0,"-","constants"],[4,0,0,"-","exceptions"],[5,0,0,"-","helpers"],[7,0,0,"-","models"]]},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","data","Python data"],"4":["py","exception","Python exception"],"5":["py","function","Python function"],"6":["py","attribute","Python attribute"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:data","4":"py:exception","5":"py:function","6":"py:attribute"},terms:{"0":[1,7],"1":[1,7],"100":[0,1],"12":1,"120":7,"168":1,"192":1,"2":[1,7],"20":1,"37":7,"404":0,"4096":[1,7],"44100":[1,7],"5":1,"512":[1,7],"5646":7,"60":7,"639":[1,7],"7":[0,1],"8":1,"9000":[1,2],"boolean":2,"byte":[0,1,5,7],"class":[0,1,2,7],"default":[0,1],"final":[1,7],"float":7,"function":[2,5],"import":6,"int":[5,7],"new":2,"return":[0,1,2,5,7],"true":[0,1,6,7],"while":[1,7],A:[2,5,7],FOR:1,For:[0,2],If:[1,2],It:0,The:[1,2,3,6,7],With:1,_transcriptionconfig:7,about:1,accept:[0,1,7],access:6,accur:1,acknowledg:7,acoust:[1,7],ad:[2,3,7],add:[1,2,6,7],add_event_handl:[2,6],add_middlewar:2,addaudio:[2,7],addit:[1,7],additional_vocab:[1,7],addpartialtranscript:[6,7],addtranscript:[2,6,7],advanc:[1,7],after:7,afterward:0,alia:0,all:[0,1,2,5,7],allow:[1,7],also:0,alter:2,an:[0,1,2,4,6,7],ani:[0,2,7],anymor:1,api:[0,1,2,3,6],appli:1,applianc:[0,1],applic:7,ar:[0,1,2,5,7],arg:2,argument:[2,6],as_config:7,asdict:7,asr:[0,1,2,3],associ:0,async:[2,5],asynchron:2,asyncio:2,asynciter:5,attach:7,au:7,audio:[0,1,2,5,6,7],audio_file_path:6,audio_set:2,audioad:7,audioset:[2,6,7],auth:[1,7],auth_head:7,auth_token:[0,1,6,7],authent:[1,7],author:[1,7],automat:[1,7],avail:[3,7],base:[2,7],batch:[0,3,6,7],batch_client:6,batch_self_service_url:3,batchclient:0,batchlanguageidentificationconfig:7,batchspeakerdiarizationconfig:7,batchtranscriptionconfig:[0,7],batchtranslationconfig:7,bearer:7,becom:7,been:[2,7],befor:1,begin:2,being:[2,6],below:6,best:2,between:7,binari:2,block:[0,2],bool:[0,2,7],buffer:[1,7],buffer_s:1,call:2,callabl:2,callback:[2,7],caller:2,can:[1,2,4,7],cancel:0,certif:1,chang:[1,5,7],channel:[1,7],channel_and_speaker_chang:1,channel_diarization_label:[1,7],charact:7,check:0,check_job_statu:0,choic:1,chunk:[1,5,7],chunk_siz:[1,5,7],clean:0,cli:6,client:[0,1,6,7],clientmessagetyp:7,close:0,code:[1,7],collect:5,com:[1,3,6],comma:1,compat:1,complet:[0,7],computation:1,conf:6,config:[0,2,7],config_fil:1,configur:[0,1,2,7],confirm:7,conjunct:2,connect:[0,2,7],connection_set:[0,2],connection_url:6,connectionset:[0,2,6,7],consol:1,constant:3,consum:2,content:[1,7],context:[0,1,7],copi:2,count:7,creat:[0,1,6],custom:[1,3,6,7],dai:[0,1],data:[1,2,5,7],de:1,debug:1,decor:5,def:6,defin:[6,7],del_non:5,delai:[1,7],delet:[0,5],delete_job:0,detect:[1,7],determin:7,diariz:[1,7],dict:[0,2,5,7],dictionari:5,directli:0,doc:2,doe:0,doesn:3,domain:[1,7],don:[2,6],e:[0,1,2,7],each:[1,5],earli:4,eg:[1,7],en:[1,2,6,7],enabl:[1,7],enable_ent:7,enable_parti:[6,7],encod:[1,7],encodingof:1,end:[2,3,4,7],endofstream:7,endoftranscript:7,endoftranscriptexcept:4,endpoint:[0,7],enforc:[1,7],enhanc:1,enterpris:[1,3,6,7],entiti:[1,7],entri:5,environ:1,error:[0,4,7],eu2:[3,6],event:[2,4,6],event_handl:[2,6],event_nam:[2,6],everi:2,exampl:[1,2,7],exceed:[2,7],except:[0,2,6],exclud:7,exist:0,expect:[1,7],expected_languag:7,expens:1,expos:2,f:6,factori:7,fail:0,fals:[0,1,7],fetch:7,fetch_data:7,fetchdata:7,field:2,file:[0,1,2,5,6,7],filenam:0,filepath:1,financ:[1,7],finish:[2,4,7],first:2,fix:[1,7],flag:1,flexibl:[1,7],foracknowledg:1,forc:[0,1,4],forceendsess:4,forcefulli:2,format:[0,1,7],found:[0,4],fr:1,from:[1,2,4,5,7],full:6,func:5,g:[0,1,7],gener:[1,7],generate_temp_token:[1,6,7],get:2,get_job_result:0,get_language_pack_info:2,github:6,given:2,global:1,gnocchi:1,h:1,ha:[2,4,7],handl:[0,1,2],handler:[2,4,6],have:3,header:7,helper:6,here:6,hertz:7,how:1,html:2,http:[0,1,2,3,7],httperror:0,httpx:0,hz:1,i:2,id:[0,1,4,7],identif:7,ignor:7,illustr:6,immedi:7,impli:2,includ:[2,7],incom:2,incomplet:7,increas:1,index:6,indic:[1,2,4,7],info:[1,7],inform:[1,2],initi:7,input:[1,5,7],insecur:1,instanti:2,intend:7,interact:2,interfac:[0,2],interpret:1,inth:1,invalid:0,invers:7,io:[2,5],iobas:[2,5],iso:[1,7],item:7,job:[0,4,7],job_id:[0,1],jobnotfoundexcept:[0,4],json:[0,1,5,7],json_utf8:5,just:2,kwarg:[0,2,7],label1:1,label2:1,label:[1,7],lambda:2,lang:1,languag:[1,2,3,6,7],language_identification_config:7,language_pack_info:2,larger:1,last:[0,1],latenc:1,later:1,latest:2,least:7,legaci:1,length:5,level:[1,7],librari:[0,2,3,4,5,7],like:[1,2,5],line:[1,7],list:[0,2,7],list_job:0,list_of_job:0,local:1,localhost:2,log:1,mai:[0,2,7],manag:[0,2],manifest:2,mark:[1,7],max:1,max_delai:[1,7],max_delay_mod:7,max_lin:7,max_line_length:7,max_sample_s:5,max_speak:7,maximum:[1,5,7],mean:7,messag:[1,2,7],message_buffer_s:7,metadata:6,method:[0,5,7],middl:1,middlewar:[2,4],min:1,mode:[6,7],model:[0,1,2,6],modul:6,more:[1,7],most:[2,7],msg:[2,6],much:1,mulaw:7,multipl:[5,7],must:[0,1,7],n:7,name:[2,6,7],need:[2,6],new_transcription_config:2,nochi:1,nokei:1,non:[1,3,7],none:[0,1,2,5,7],normal:7,note:3,notif:7,notification_config:7,notificationconfig:7,number:[1,7],oauth2:7,object:[0,2,5],one:1,onli:[1,2,7],open:[0,6],oper:1,operating_point:7,optim:7,option:[0,1,7],order:4,os:0,other:[0,1],out:2,outgo:2,output:[1,5,7],output_local:7,overhead:1,overrid:1,overriden:7,own:[1,7],pack:[1,2,7],page:6,paramet:[0,2,5,6,7],part:[6,7],partial:[1,6,7],particular:2,pass:[0,2],path:[0,6],pathlik:0,pcm_f32le:[1,7],pcm_s16le:7,per:7,permit:[1,7],piec:1,ping:7,ping_timeout_second:7,place:5,plaintext:1,pleas:6,point:1,pong:7,pool:0,possibl:[1,2],post:7,potenti:7,pre:1,prefer:2,preset:1,previous:[0,7],print:[1,2,6],print_partial_transcript:6,print_transcript:6,probabl:2,process:[1,2],produc:[2,7],producer_consum:2,product:1,provid:[1,6],puctuat:7,punctuat:[1,7],punctuation_overrid:7,punctuation_permitted_mark:1,punctuation_sensit:1,put:7,queri:7,rais:[0,2,4,5],rate:[1,7],rather:1,raw:[1,7],rb:6,re:[2,7],read:[1,2,5],read_in_chunk:5,readm:6,readthedoc:2,real:[1,2,7],realtim:[3,6],receipt:7,receiv:[1,2],recognisedent:1,recognit:[2,7],recognitionstart:[2,7],recurs:[5,7],redirect:1,refer:2,regist:6,regular:1,remov:1,repres:1,request:[0,1,7],requir:[0,1],respect:1,respond:2,respons:[0,7],rest:0,result:[0,2],retain:1,retriev:1,rfc:7,rt:[3,6,7],rt_self_service_url:3,rtspeakerdiarizationconfig:7,run:[0,1,2],run_synchron:[2,6],s:[1,5,7],saa:[0,1,7],sampl:[1,7],sample_r:[1,7],sc:1,search:6,second:[2,7],section:7,see:6,select:1,self:[1,3],semaphor:7,semaphore_timeout_second:7,send:[0,1,7],send_request:0,sensit:[1,7],sent:[2,7],separ:1,sequenc:5,server:[1,2,7],servermessagetyp:[2,6,7],servic:3,session:[2,4,7],set:[0,2,6,7],setrecognitionconfig:[2,7],share:1,should:[1,2,7],show:1,sign:1,simpl:[1,2],singl:[1,7],size:[1,5,7],small:1,sound:1,sourc:[0,2,4,5,7],space:[1,7],speaker:[1,7],speaker_chang:1,speaker_change_sensit:[1,7],speaker_diarization_config:7,speaker_diarization_max_speak:1,speaker_diarization_sensit:1,speaker_sensit:7,special:1,specif:7,specifi:[1,7],speech:1,srt:[0,1,7],srt_overrid:7,srtoverrid:7,ssl:[1,7],ssl_context:7,sslcontext:7,standard:[1,7],start:7,startrecognit:7,statu:[0,7],stderr:1,stdout:1,still:0,stop:2,str:[0,2,7],stream:[1,2,5,7],sub:6,submit:0,submit_job:0,subset:2,subtitl:7,successfulli:7,suppli:7,support:7,symbol:1,synchron:2,t:[2,3,6],target:[1,7],target_languag:7,task:2,temp:1,temporari:[1,7],termin:0,text:7,than:[0,1],thei:[2,7],thi:[0,1,2,5,6,7],threshold:7,time:[1,2,7],timeout:[2,7],timeouterror:2,token:[0,1,6,7],too:1,tool:6,transcrib:6,transcript:[0,1,2,4,6,7],transcription_config:[0,2],transcription_format:0,transcriptionconfig:[2,6,7],transcriptionerror:[0,4],translat:[1,7],translation_config:7,translation_target_languag:1,tupl:0,turn:5,txt:[0,1],type:[0,1,2,5,7],unbreak:1,union:0,unnecessari:1,unset:0,until:[0,2,7],up:0,updat:[1,2],update_transcription_config:2,url:[0,1,2,3,6,7],us:[0,1,2,3,4,5,7],usag:1,user:[2,4],util:5,v2:[0,1,2,3,6],v:1,valid:[0,1,2],valu:[1,5,7],valueerror:[2,5],variou:7,verbos:1,via:2,vocab:1,vocab_filepath:1,vocabulari:7,vv:1,wa:[1,4,5],wai:2,wait:1,wait_for_complet:0,warn:7,wav:6,waveform:6,we:[0,2],websocket:[1,2,7],websocketcli:[2,6],when:[0,1,2,7],where:[1,5,7],wherev:1,whether:[1,2,7],which:[0,1,2,5,7],white:7,wire:1,within:[0,1,7],word:7,work:1,would:7,wrap:7,wrapper:[0,2,6],ws:6,wss:[1,2,3,6],yet:2,yield:5,you:[0,1,2],your:[1,7]},titles:["speechmatics.batch_client","Speechmatics CLI Tool","speechmatics.client","speechmatics.client","speechmatics.exceptions","speechmatics.helpers","speechmatics-python","speechmatics.models"],titleterms:{argument:1,batch:1,batch_client:0,cli:1,client:[2,3],command:[1,6],config:1,delet:1,exampl:6,except:4,get:1,helper:5,indic:6,job:1,librari:6,line:6,list:1,mode:1,model:7,name:1,posit:1,python:6,refer:6,result:1,rt:1,set:1,speechmat:[0,1,2,3,4,5,6,7],statu:1,sub:1,submit:1,tabl:6,tool:1,transcrib:1,unset:1,usag:6}})
\ No newline at end of file
diff --git a/requirements-dev.txt b/requirements-dev.txt
index fc5bdbb..490a553 100644
--- a/requirements-dev.txt
+++ b/requirements-dev.txt
@@ -9,3 +9,4 @@ sphinx==4.4.0
pytest-cov==3.0.0
black==22.3.0
sphinx-argparse==0.4.0
+pytest_httpx==0.21.3
\ No newline at end of file
diff --git a/speechmatics/cli.py b/speechmatics/cli.py
index 2901652..057c6a7 100755
--- a/speechmatics/cli.py
+++ b/speechmatics/cli.py
@@ -36,6 +36,7 @@
BatchSpeakerDiarizationConfig,
RTSpeakerDiarizationConfig,
BatchTranslationConfig,
+ BatchLanguageIdentificationConfig,
)
from speechmatics.cli_parser import (
parse_args,
@@ -198,6 +199,11 @@ def get_transcription_config(args): # pylint: disable=too-many-branches
# Ensure "en" is the default language as to not break existing API behavior.
config = {"language": "en"}
+ # transcription_config is flattened in the BatchTranscriptionConfig,
+ # so the config entry from JSON must be flattened here, otherwise the JSON entry would be ignored
+ if config.get("transcription_config"):
+ config.update(config.pop("transcription_config"))
+
# Explicit command line arguments override values from config file.
for option in [
"language",
@@ -267,6 +273,12 @@ def get_transcription_config(args): # pylint: disable=too-many-branches
target_languages=translation_target_languages.split(",")
)
+ if args.get("langid_expected_languages") is not None:
+ langid_expected_languages = args.get("langid_expected_languages")
+ config["language_identification_config"] = BatchLanguageIdentificationConfig(
+ expected_languages=langid_expected_languages.split(",")
+ )
+
if args["mode"] == "rt":
# pylint: disable=unexpected-keyword-arg
return TranscriptionConfig(**config)
diff --git a/speechmatics/cli_parser.py b/speechmatics/cli_parser.py
index d9644c3..b9343f7 100644
--- a/speechmatics/cli_parser.py
+++ b/speechmatics/cli_parser.py
@@ -216,6 +216,14 @@ def get_arg_parser():
default=None,
help=("Comma-separated list of languages to translate the transcription into"),
)
+ config_parser.add_argument(
+ "--langid-langs",
+ "--langid-languages",
+ dest="langid_expected_languages",
+ type=str,
+ default=None,
+ help=("Comma-separated list of expected languages for language identification"),
+ )
# Parent parser for output type
output_format_parser = argparse.ArgumentParser(add_help=False)
diff --git a/speechmatics/models.py b/speechmatics/models.py
index 3b6461e..178e32e 100644
--- a/speechmatics/models.py
+++ b/speechmatics/models.py
@@ -143,6 +143,14 @@ class BatchTranslationConfig:
"""Target languages for which translation should be produced"""
+@dataclass
+class BatchLanguageIdentificationConfig:
+ """Batch mode: Language identification config."""
+
+ expected_languages: List[str] = None
+ """Expected languages for language identification"""
+
+
@dataclass(init=False)
class TranscriptionConfig(_TranscriptionConfig):
"""Real-time: Defines transcription parameters."""
@@ -179,6 +187,9 @@ class BatchTranscriptionConfig(_TranscriptionConfig):
notification_config: NotificationConfig = None
"""Optional configuration for callback notification."""
+ language_identification_config: BatchLanguageIdentificationConfig = None
+ """Optional configuration for language identification."""
+
translation_config: BatchTranslationConfig = None
"""Optional configuration for translation."""
@@ -196,6 +207,9 @@ def as_config(self):
fetch_data = dictionary.pop("fetch_data", None)
notification_config = dictionary.pop("notification_config", None)
+ language_identification_config = dictionary.pop(
+ "language_identification_config", None
+ )
translation_config = dictionary.pop("translation_config", None)
srt_overrides = dictionary.pop("srt_overrides", None)
@@ -209,6 +223,9 @@ def as_config(self):
notification_config = [notification_config]
config["notification_config"] = notification_config
+ if language_identification_config:
+ config["language_identification_config"] = language_identification_config
+
if translation_config:
config["translation_config"] = translation_config
diff --git a/tests/data/batch-job-status.json b/tests/data/batch-job-status.json
new file mode 100644
index 0000000..a13e9b0
--- /dev/null
+++ b/tests/data/batch-job-status.json
@@ -0,0 +1,18 @@
+{
+ "job": {
+ "config": {
+ "fetch_data": {
+ "url": "https://smtooling.blob.core.windows.net/short-files/15sec.wav"
+ },
+ "transcription_config": {
+ "language": "en"
+ },
+ "type": "transcription"
+ },
+ "created_at": "2023-02-22T14:33:02.221Z",
+ "data_name": "",
+ "duration": 15,
+ "id": "p8t3dcrign",
+ "status": "done"
+ }
+}
\ No newline at end of file
diff --git a/tests/data/batch-job-transcript.json b/tests/data/batch-job-transcript.json
new file mode 100644
index 0000000..c398a36
--- /dev/null
+++ b/tests/data/batch-job-transcript.json
@@ -0,0 +1,321 @@
+{
+ "format": "2.8",
+ "job": {
+ "created_at": "2023-02-22T14:33:02.221Z",
+ "data_name": "",
+ "duration": 15,
+ "id": "p8t3dcrign"
+ },
+ "metadata": {
+ "created_at": "2023-02-22T14:33:02.221Z",
+ "language_pack_info": {
+ "adapted": false,
+ "itn": true,
+ "language_description": "English",
+ "word_delimiter": "",
+ "writing_direction": "left-to-right"
+ },
+ "transcription_config": {
+ "language": "en"
+ },
+ "type": "transcription"
+ },
+ "results": [
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "Tidy",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 1.83,
+ "start_time": 1.41,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "things",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 2.1,
+ "start_time": 1.83,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "up",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 2.37,
+ "start_time": 2.1,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": ".",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "attaches_to": "previous",
+ "end_time": 2.37,
+ "is_eos": true,
+ "start_time": 2.37,
+ "type": "punctuation"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "Place",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 3.75,
+ "start_time": 3.42,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 0.87,
+ "content": "your",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 3.84,
+ "start_time": 3.75,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 0.87,
+ "content": "shelves",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 4.23,
+ "start_time": 3.84,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "on",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 4.35,
+ "start_time": 4.23,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "the",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 4.44,
+ "start_time": 4.35,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 0.98,
+ "content": "rungs",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 5.01,
+ "start_time": 4.44,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": ".",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "attaches_to": "previous",
+ "end_time": 5.01,
+ "is_eos": true,
+ "start_time": 5.01,
+ "type": "punctuation"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 0.51,
+ "content": "Ensure",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 6.6,
+ "start_time": 6.13,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 0.54,
+ "content": "the",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 6.69,
+ "start_time": 6.6,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": ".",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "attaches_to": "previous",
+ "end_time": 6.69,
+ "is_eos": true,
+ "start_time": 6.69,
+ "type": "punctuation"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "Fill",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 8.91,
+ "start_time": 8.49,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "with",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 9.09,
+ "start_time": 8.91,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "your",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 9.21,
+ "start_time": 9.09,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 0.6,
+ "content": "favourite",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 9.84,
+ "start_time": 9.21,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": "things",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 10.47,
+ "start_time": 9.84,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": ".",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "attaches_to": "previous",
+ "end_time": 10.47,
+ "is_eos": true,
+ "start_time": 10.47,
+ "type": "punctuation"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 0.26,
+ "content": "Whyalla",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "end_time": 12.3,
+ "start_time": 11.74,
+ "type": "word"
+ },
+ {
+ "alternatives": [
+ {
+ "confidence": 1.0,
+ "content": ".",
+ "language": "en",
+ "speaker": "UU"
+ }
+ ],
+ "attaches_to": "previous",
+ "end_time": 12.3,
+ "is_eos": true,
+ "start_time": 12.3,
+ "type": "punctuation"
+ }
+ ]
+}
diff --git a/tests/test_cli.py b/tests/test_cli.py
index cef11dc..ee2fa8b 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -234,6 +234,16 @@
"output_format": "json-v2",
},
),
+ (
+ [
+ "batch",
+ "submit",
+ "--langid-langs=de,es,cs",
+ ],
+ {
+ "langid_expected_languages": "de,es,cs",
+ },
+ ),
],
)
def test_cli_arg_parse_with_file(args, values):
diff --git a/tests/test_client.py b/tests/test_client.py
index aa9c834..ab86416 100644
--- a/tests/test_client.py
+++ b/tests/test_client.py
@@ -9,14 +9,18 @@
import asynctest
import pytest
+from pytest_httpx import HTTPXMock
from speechmatics import client
+from speechmatics.batch_client import BatchClient
from speechmatics.exceptions import ForceEndSession
from speechmatics.models import (
ConnectionSettings,
ServerMessageType,
ClientMessageType,
RTSpeakerDiarizationConfig,
+ BatchTranscriptionConfig,
)
+
from tests.utils import path_to_test_resource, default_ws_client_setup
@@ -537,6 +541,41 @@ def test_language_pack_info_is_stored(mock_server):
assert info["language_code"] == "en"
+def test_batch_mock_jobs(httpx_mock: HTTPXMock):
+ # submit job
+ httpx_mock.add_response(content=b'{"id":"p8t3dcrign"}')
+
+ # check job status
+ with open(path_to_test_resource("batch-job-status.json"), "rb") as file:
+ job_status = file.read()
+ httpx_mock.add_response(content=job_status)
+
+ # get job result
+ with open(path_to_test_resource("batch-job-transcript.json"), "rb") as file:
+ transcript = file.read()
+ httpx_mock.add_response(content=transcript)
+
+ settings = ConnectionSettings(
+ url="https://speechmatics.com/foo/v2",
+ auth_token="bar",
+ )
+
+ conf = BatchTranscriptionConfig(
+ language="en",
+ )
+
+ with BatchClient(settings) as batch_client:
+ job_id = batch_client.submit_job(
+ audio=("foo", b"some audio data"),
+ transcription_config=conf,
+ )
+
+ actual_transcript = batch_client.wait_for_completion(
+ job_id, transcription_format="txt"
+ )
+ assert transcript.decode("utf-8") == actual_transcript
+
+
def deepcopy_state(obj):
"""
Return a deepcopy of the __dict__ (or state) of an object but ignore