Update README.md
Browse files
README.md
CHANGED
@@ -66,6 +66,16 @@ additional postprocessing stacks integrated as [`pipeline`](https://huggingface.
|
|
66 |
These libraries are merged into Kotoba-Whisper-v1.1 via pipeline and will be applied seamlessly to the predicted transcription from [kotoba-tech/kotoba-whisper-v1.0](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0).
|
67 |
The pipeline has been developed through the collaboration between [Asahi Ushio](https://asahiushio.com) and [Kotoba Technologies](https://twitter.com/kotoba_tech)
|
68 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
## Transformers Usage
|
70 |
Kotoba-Whisper-v1.1 is supported in the Hugging Face 🤗 Transformers library from version 4.39 onwards. To run the model, first
|
71 |
install the latest version of Transformers.
|
|
|
66 |
These libraries are merged into Kotoba-Whisper-v1.1 via pipeline and will be applied seamlessly to the predicted transcription from [kotoba-tech/kotoba-whisper-v1.0](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0).
|
67 |
The pipeline has been developed through the collaboration between [Asahi Ushio](https://asahiushio.com) and [Kotoba Technologies](https://twitter.com/kotoba_tech)
|
68 |
|
69 |
+
|
70 |
+
Following table presents the raw CER (unlike usual CER where the punctuations are removed before computing the metrics).
|
71 |
+
|
72 |
+
| model | CommonVoice 8.0 (Japanese) | JSUT Basic 5000 | ReazonSpeech Test |
|
73 |
+
|:--------------------------------|---------------------------------------:|-------------------------------------:|----------------------------------------:|
|
74 |
+
| kotoba-tech/kotoba-whisper-v1.0 | 17.8 | 15.2 | 17.8 |
|
75 |
+
| kotoba-tech/kotoba-whisper-v1.1 | 16 | 11.6 | 18.5 |
|
76 |
+
| openai/whisper-large-v3 | 15.4 | 13.6 | 20.7 |
|
77 |
+
|
78 |
+
|
79 |
## Transformers Usage
|
80 |
Kotoba-Whisper-v1.1 is supported in the Hugging Face 🤗 Transformers library from version 4.39 onwards. To run the model, first
|
81 |
install the latest version of Transformers.
|