Update README.md
Browse files
README.md
CHANGED
@@ -47,7 +47,7 @@ We compare our kotoba-whisper-bilingual with OpenAI whisper models, kotoba-whisp
|
|
47 |
OpenAI whisper is not trained for English to Japanese speech-to-text translation, and other models are specific to the Task (eg. kotoba-whisper is Japanese ASR and
|
48 |
distil whisper is English ASR only).
|
49 |
|
50 |
-
### Speech2Text Translation (Japanese->English)
|
51 |
|
52 |
| model | [CoVoST2 (Ja->En)](https://huggingface.co/datasets/japanese-asr/ja2en.s2t_translation)| [Fleurs (Ja->En)](https://huggingface.co/datasets/japanese-asr/ja2en.s2t_translation) |
|
53 |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------:|------------------------------------------------------------------------------------------------------:|
|
@@ -65,7 +65,7 @@ distil whisper is English ASR only).
|
|
65 |
| [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 377.2 | 474 |
|
66 |
|
67 |
|
68 |
-
### Speech2Text Translation (English->Japanese)
|
69 |
|
70 |
| model | [CoVoST2 (En->Ja)](https://huggingface.co/datasets/japanese-asr/en2ja.s2t_translation)| [Fleurs (En->JA)](https://huggingface.co/datasets/japanese-asr/en2ja.s2t_translation) |
|
71 |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------:|------------------------------------------------------------------------------------------------------:|
|
@@ -83,7 +83,7 @@ distil whisper is English ASR only).
|
|
83 |
| [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 185.2 | 200.5 |
|
84 |
|
85 |
|
86 |
-
### ASR (Japanese)
|
87 |
|
88 |
| 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) |
|
89 |
|:--------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------:|----------------------------------------------------------------------------------------:|------------------------------------------------------------------------------------------------------------:|
|
@@ -101,7 +101,7 @@ distil whisper is English ASR only).
|
|
101 |
|
102 |
|
103 |
|
104 |
-
### ASR (English)
|
105 |
|
106 |
| model | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (ami) | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (earnings22) | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (librispeech) | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (tedlium) | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (voxpopuli) |
|
107 |
|:----------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------:|-----------------------------------------------------------------------------------:|------------------------------------------------------------------------------------:|--------------------------------------------------------------------------------:|----------------------------------------------------------------------------------:|
|
|
|
47 |
OpenAI whisper is not trained for English to Japanese speech-to-text translation, and other models are specific to the Task (eg. kotoba-whisper is Japanese ASR and
|
48 |
distil whisper is English ASR only).
|
49 |
|
50 |
+
### Speech2Text Translation (Japanese->English): WER
|
51 |
|
52 |
| model | [CoVoST2 (Ja->En)](https://huggingface.co/datasets/japanese-asr/ja2en.s2t_translation)| [Fleurs (Ja->En)](https://huggingface.co/datasets/japanese-asr/ja2en.s2t_translation) |
|
53 |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------:|------------------------------------------------------------------------------------------------------:|
|
|
|
65 |
| [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 377.2 | 474 |
|
66 |
|
67 |
|
68 |
+
### Speech2Text Translation (English->Japanese): CER
|
69 |
|
70 |
| model | [CoVoST2 (En->Ja)](https://huggingface.co/datasets/japanese-asr/en2ja.s2t_translation)| [Fleurs (En->JA)](https://huggingface.co/datasets/japanese-asr/en2ja.s2t_translation) |
|
71 |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------:|------------------------------------------------------------------------------------------------------:|
|
|
|
83 |
| [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 185.2 | 200.5 |
|
84 |
|
85 |
|
86 |
+
### ASR (Japanese): CER
|
87 |
|
88 |
| 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) |
|
89 |
|:--------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------:|----------------------------------------------------------------------------------------:|------------------------------------------------------------------------------------------------------------:|
|
|
|
101 |
|
102 |
|
103 |
|
104 |
+
### ASR (English): WER
|
105 |
|
106 |
| model | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (ami) | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (earnings22) | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (librispeech) | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (tedlium) | [ESB](https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval) (voxpopuli) |
|
107 |
|:----------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------:|-----------------------------------------------------------------------------------:|------------------------------------------------------------------------------------:|--------------------------------------------------------------------------------:|----------------------------------------------------------------------------------:|
|