Merge pull request #254 from megagonlabs/develop

Release v5.1.3

README.md

@@ -93,7 +93,7 @@ $ pip install -U ginza https://github.com/megagonlabs/ginza/releases/download/la
 
 If you hope to accelarate the transformers-based models by using GPUs with CUDA support, you can install `spacy` by specifying the CUDA version as follows:
 ```console
-pip install -U "spacy[cuda110]"
+pip install -U "spacy[cuda117]"
 ```
 
 And you need to install a version of pytorch that is consistent with the CUDA version.
@@ -108,6 +108,11 @@ Then, install the latest version of `ginza` and `ja_ginza`:
 $ pip install -U ginza ja_ginza
 ```
 
+When using Apple Silicon such as M1 or M2, you can accelerate the analysis process by installing `thinc-apple-ops`:
+```console
+$ pip install torch thinc-apple-ops
+```
+
 ### Execute ginza command
 Run `ginza` command from the console, then input some Japanese text.
 After pressing enter key, you will get the parsed results with [CoNLL-U Syntactic Annotation](https://universaldependencies.org/format.html#syntactic-annotation) format.
@@ -234,6 +239,11 @@ Please read the official documents to compile user dictionaries with `sudachipy`
 
 ### version 5.x
 
+#### ginza-5.1.3
+- 2023-09-25
+- Migrate to spaCy v3.6
+- Beta release of `ja_ginza_bert_large`
+
 #### ginza-5.1.2
 - 2022-03-12
 - Migrate to spaCy v3.4

config/ja_ginza.meta.json

@@ -1,7 +1,7 @@
 {
   "lang":"ja",
   "name":"ginza",
-  "version":"5.1.2",
+  "version":"5.1.3",
   "description":"Japanese multi-task CNN trained on UD-Japanese BCCWJ r2.8 + GSK2014-A(2019). Assigns word2vec token vectors. Components: tok2vec, parser, ner, morphologizer, atteribute_ruler, compound_splitter, bunsetu_recognizer.",
   "author":"Megagon Labs Tokyo.",
   "email":"[email protected]",
@@ -34,7 +34,14 @@
     }
   ],
   "parent_package":"spacy",
-  "spacy_version":">=3.2.0,<3.5.0",
+  "spacy_version":">=3.2.0,<3.7.0",
+  "spacy_git_version":"0fc3dee77",
+  "vectors":{
+    "width":300,
+    "vectors":20000,
+    "keys":480443,
+    "name":"ja_vectors"
+  },
   "pipeline":[
     "tok2vec",
     "parser",
@@ -53,7 +60,7 @@
     "compound_splitter",
     "bunsetu_recognizer"
   ],
-  "disabled": [
+  "disabled":[
     "attribute_ruler"
   ],
   "requirements":[