init
Browse files
README.md
CHANGED
|
@@ -19,39 +19,8 @@ additional postprocessing stacks integrated as [`pipeline`](https://huggingface.
|
|
| 19 |
These libraries are merged into Kotoba-Whisper-v2.1 via pipeline and will be applied seamlessly to the predicted transcription from [kotoba-tech/kotoba-whisper-v2.0](https://huggingface.co/kotoba-tech/kotoba-whisper-v2.0).
|
| 20 |
The pipeline has been developed through the collaboration between [Asahi Ushio](https://asahiushio.com) and [Kotoba Technologies](https://twitter.com/kotoba_tech)
|
| 21 |
|
| 22 |
-
|
| 23 |
-
Following table presents the raw CER (unlike usual CER where the punctuations are removed before computing the metrics, see the evaluation script [here](https://huggingface.co/kotoba-tech/kotoba-whisper-v2.1/blob/main/run_short_form_eval.py))
|
| 24 |
-
along with the.
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
| model | [CommonVoice 8 (Japanese test set)](https://huggingface.co/datasets/japanese-asr/ja_asr.common_voice_8_0) | [JSUT Basic 5000](https://huggingface.co/datasets/japanese-asr/ja_asr.jsut_basic5000) | [ReazonSpeech (held out test set)](https://huggingface.co/datasets/japanese-asr/ja_asr.reazonspeech_test) |
|
| 28 |
-
|:--------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------:|----------------------------------------------------------------------------------------:|------------------------------------------------------------------------------------------------------------:|
|
| 29 |
-
| [kotoba-tech/kotoba-whisper-v2.0](https://huggingface.co/kotoba-tech/kotoba-whisper-v2.0) | 17.6 | 15.4 | 17.4 |
|
| 30 |
-
| [kotoba-tech/kotoba-whisper-v2.1](https://huggingface.co/kotoba-tech/kotoba-whisper-v2.1) | 17.7 | 15.4 | 17 |
|
| 31 |
-
| [kotoba-tech/kotoba-whisper-v2.1](https://huggingface.co/kotoba-tech/kotoba-whisper-v2.1) (punctuator + stable-ts) | 17.7 | 15.4 | 17 |
|
| 32 |
-
| [kotoba-tech/kotoba-whisper-v2.1](https://huggingface.co/kotoba-tech/kotoba-whisper-v2.1) (punctuator) | 17.7 | 15.4 | 17 |
|
| 33 |
-
| [kotoba-tech/kotoba-whisper-v2.1](https://huggingface.co/kotoba-tech/kotoba-whisper-v2.1) (stable-ts) | 17.7 | 15.4 | 17 |
|
| 34 |
-
| [kotoba-tech/kotoba-whisper-v1.0](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0) | 17.8 | 15.2 | 17.8 |
|
| 35 |
-
| [kotoba-tech/kotoba-whisper-v1.1](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.1) | 17.9 | 15 | 17.8 |
|
| 36 |
-
| [kotoba-tech/kotoba-whisper-v1.1](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.1) (punctuator + stable-ts) | 17.9 | 15 | 17.8 |
|
| 37 |
-
| [kotoba-tech/kotoba-whisper-v1.1](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.1) (punctuator) | 17.9 | 15 | 17.8 |
|
| 38 |
-
| [kotoba-tech/kotoba-whisper-v1.1](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.1) (stable-ts) | 17.9 | 15 | 17.8 |
|
| 39 |
-
| [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) | 15.3 | 13.4 | 20.5 |
|
| 40 |
-
| [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) | 15.9 | 10.6 | 34.6 |
|
| 41 |
-
| [openai/whisper-large](https://huggingface.co/openai/whisper-large) | 16.6 | 11.3 | 40.7 |
|
| 42 |
-
| [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) | 17.9 | 13.1 | 39.3 |
|
| 43 |
-
| [openai/whisper-base](https://huggingface.co/openai/whisper-base) | 34.5 | 26.4 | 76 |
|
| 44 |
-
| [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 21.5 | 18.9 | 48.1 |
|
| 45 |
-
| [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 58.8 | 38.3 | 153.3 |
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
Regarding to the normalized CER, since those update from v2.1 will be removed by the normalization, kotoba-tech/kotoba-whisper-v2.1 marks the same CER values as [kotoba-tech/kotoba-whisper-v2.0](https://huggingface.co/kotoba-tech/kotoba-whisper-v2.0).
|
| 49 |
-
|
| 50 |
-
### Latency
|
| 51 |
-
Please refer to the section of the latency in the kotoba-whisper-v1.1 [here](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.1#latency).
|
| 52 |
-
|
| 53 |
## Transformers Usage
|
| 54 |
-
Kotoba-Whisper-v2.
|
| 55 |
install the latest version of Transformers.
|
| 56 |
|
| 57 |
```bash
|
|
@@ -61,6 +30,8 @@ pip install "punctuators==0.0.5"
|
|
| 61 |
pip install "pyannote.audio"
|
| 62 |
pip install git+https://github.com/huggingface/diarizers.git
|
| 63 |
```
|
|
|
|
|
|
|
| 64 |
|
| 65 |
### Transcription
|
| 66 |
The model can be used with the [`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline)
|
|
|
|
| 19 |
These libraries are merged into Kotoba-Whisper-v2.1 via pipeline and will be applied seamlessly to the predicted transcription from [kotoba-tech/kotoba-whisper-v2.0](https://huggingface.co/kotoba-tech/kotoba-whisper-v2.0).
|
| 20 |
The pipeline has been developed through the collaboration between [Asahi Ushio](https://asahiushio.com) and [Kotoba Technologies](https://twitter.com/kotoba_tech)
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
## Transformers Usage
|
| 23 |
+
Kotoba-Whisper-v2.2 is supported in the Hugging Face 🤗 Transformers library from version 4.39 onwards. To run the model, first
|
| 24 |
install the latest version of Transformers.
|
| 25 |
|
| 26 |
```bash
|
|
|
|
| 30 |
pip install "pyannote.audio"
|
| 31 |
pip install git+https://github.com/huggingface/diarizers.git
|
| 32 |
```
|
| 33 |
+
Also,
|
| 34 |
+
|
| 35 |
|
| 36 |
### Transcription
|
| 37 |
The model can be used with the [`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline)
|