Fix ctm format, fix normalizers

speechmatics · Nov 9, 2023 · e81cb15 · e81cb15
1 parent 9fcc69d
commit e81cb15
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 1 deletion.
diff --git a/metrics/diarization/sm_diarization_metrics/cookbook.py b/metrics/diarization/sm_diarization_metrics/cookbook.py
@@ -399,7 +399,7 @@ def get_unknown_speaker_count_for_files(hypothesis_file: str) -> int:
     Speaker labels of punctuations are not considered.
     If the input file is not in v2 json format, "0" will be returned."""
     hypothesis_file_extension = hypothesis_file.split(".")[-1]
-    if hypothesis_file_extension == "lab":
+    if hypothesis_file_extension == "lab" or "ctm":
         # unknown_speaker only supported for v2 json
         return 0
     entries = utils.load_v2_json_file(hypothesis_file, get_content_type=True)

diff --git a/metrics/wer/normalizers/__init__.py b/metrics/wer/normalizers/__init__.py
@@ -0,0 +1,2 @@
+from .basic import BasicTextNormalizer as BasicTextNormalizer
+from .english import EnglishTextNormalizer as EnglishTextNormalizer
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		from .basic import BasicTextNormalizer as BasicTextNormalizer
		from .english import EnglishTextNormalizer as EnglishTextNormalizer