Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,8 @@ and [facebook/nllb-200-3.3B](https://huggingface.co/facebook/nllb-200-3.3B) for
|
|
| 13 |
The input must be Japanese speech, while the translation can be in any languages NLLB trained on. Please find the all available languages and their language codes
|
| 14 |
[here](https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200).
|
| 15 |
|
|
|
|
|
|
|
| 16 |
## Benchmark
|
| 17 |
The folloiwng table shows WER computed over the reference and predicted translation for translating Japanse speech to English text task
|
| 18 |
(subsets of [CoVoST2 and Fleurs](https://huggingface.co/datasets/japanese-asr/ja2en.s2t_translation)) with different size of NLLB along with OpenAI Whisper models.
|
|
|
|
| 13 |
The input must be Japanese speech, while the translation can be in any languages NLLB trained on. Please find the all available languages and their language codes
|
| 14 |
[here](https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200).
|
| 15 |
|
| 16 |
+
**Model for English speech translation is available at [en-cascaded-s2t-translation](https://huggingface.co/japanese-asr/en-cascaded-s2t-translation).**
|
| 17 |
+
|
| 18 |
## Benchmark
|
| 19 |
The folloiwng table shows WER computed over the reference and predicted translation for translating Japanse speech to English text task
|
| 20 |
(subsets of [CoVoST2 and Fleurs](https://huggingface.co/datasets/japanese-asr/ja2en.s2t_translation)) with different size of NLLB along with OpenAI Whisper models.
|