Update README.md
Browse files
README.md
CHANGED
|
@@ -283,6 +283,11 @@ Then pass `attn_implementation="flash_attention_2"` to `from_pretrained`:
|
|
| 283 |
See [https://huggingface.co/distil-whisper/distil-large-v3#model-details](https://huggingface.co/distil-whisper/distil-large-v3#model-details).
|
| 284 |
|
| 285 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 286 |
## Evaluation
|
| 287 |
The following code-snippets demonstrates how to evaluate the kotoba-whisper model on the Japanese subset of the CommonVoice 8.0.
|
| 288 |
First, we need to install the required packages, including 🤗 Datasets to load the audio data, and 🤗 Evaluate to
|
|
|
|
| 283 |
See [https://huggingface.co/distil-whisper/distil-large-v3#model-details](https://huggingface.co/distil-whisper/distil-large-v3#model-details).
|
| 284 |
|
| 285 |
|
| 286 |
+
## Training
|
| 287 |
+
Please refer to [https://github.com/kotoba-tech/kotoba-whisper](https://github.com/kotoba-tech/kotoba-whisper) for the model training detail.
|
| 288 |
+
Datasets used in distillation and the whole model variations can be found at [https://huggingface.co/japanese-asr](https://huggingface.co/japanese-asr).
|
| 289 |
+
|
| 290 |
+
|
| 291 |
## Evaluation
|
| 292 |
The following code-snippets demonstrates how to evaluate the kotoba-whisper model on the Japanese subset of the CommonVoice 8.0.
|
| 293 |
First, we need to install the required packages, including 🤗 Datasets to load the audio data, and 🤗 Evaluate to
|