-
japanese-asr/en2ja.s2t_translation
Viewer • Updated • 32k • 14 • 2 -
japanese-asr/ja2en.s2t_translation
Viewer • Updated • 2.24k • 27 • 1 -
japanese-asr/ja-cascaded-s2t-translation
Automatic Speech Recognition • 0.8B • Updated • 6 • 4 -
japanese-asr/en-cascaded-s2t-translation
Automatic Speech Recognition • 0.8B • Updated • 1 • 1
AI & ML interests
This repo contains models and datasets for Japanese ASR. See our main model https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0.
Japanese ASR Models
-
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-all
0.8B • Updated • 30 • 4 -
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-large
Automatic Speech Recognition • 0.8B • Updated • 30 • 5 -
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-medium
Automatic Speech Recognition • 0.8B • Updated • 6 • 2 -
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-tiny
Automatic Speech Recognition • 0.8B • Updated • 5 • 1
These are the collection of the Japanese ASR datasets labelled by the whisper-large-v3 (WER filter applied).
-
japanese-asr/whisper_transcriptions.reazonspeech.tiny.wer_10.0
Viewer • Updated • 1.77k • 13 -
japanese-asr/whisper_transcriptions.reazonspeech.small.wer_10.0
Viewer • Updated • 20.9k • 9 -
japanese-asr/whisper_transcriptions.reazonspeech.medium.wer_10.0
Viewer • Updated • 209k • 52 -
japanese-asr/whisper_transcriptions.reazonspeech.large.wer_10.0
Viewer • Updated • 1.04M • 33
ASR Evaluation Dataset
These are the collection of the Bilingual ASR datasets labelled by the whisper-large-v3. The dataset consists of ASR and S2T translation tasks.
-
japanese-asr/en_asr.mls
Viewer • Updated • 10.4M • 848 • 2 -
japanese-asr/whisper_transcriptions.mls
Viewer • Updated • 10.4M • 1.28k • 1 -
japanese-asr/whisper_transcriptions.mls.wer_10.0
Viewer • Updated • 9.33M • 705 • 1 -
japanese-asr/whisper_transcriptions.mls.wer_10.0.vectorized
Viewer • Updated • 7.44M • 2.27k • 1
These are the collection of the Japanese ASR datasets labelled by the whisper-large-v3.
-
japanese-asr/whisper_transcriptions.reazonspeech.tiny
Viewer • Updated • 5.32k • 18 -
japanese-asr/whisper_transcriptions.reazonspeech.small
Viewer • Updated • 62k • 36 • 2 -
japanese-asr/whisper_transcriptions.reazonspeech.medium
Viewer • Updated • 619k • 38 -
japanese-asr/whisper_transcriptions.reazonspeech.large
Viewer • Updated • 3.1M • 41
These are the collection of the Japanese ASR datasets labelled by the whisper-large-v3 (WER filter applied and transformed into logmel feature).
-
japanese-asr/whisper_transcriptions.reazonspeech.tiny.wer_10.0.vectorized
Viewer • Updated • 1.77k • 10 -
japanese-asr/whisper_transcriptions.reazonspeech.small.wer_10.0.vectorized
Viewer • Updated • 3.22k • 33 -
japanese-asr/whisper_transcriptions.reazonspeech.medium.wer_10.0.vectorized
Viewer • Updated • 3.26k • 20 -
japanese-asr/whisper_transcriptions.reazonspeech.large.wer_10.0.vectorized
Viewer • Updated • 3.26k • 47
-
japanese-asr/en2ja.s2t_translation
Viewer • Updated • 32k • 14 • 2 -
japanese-asr/ja2en.s2t_translation
Viewer • Updated • 2.24k • 27 • 1 -
japanese-asr/ja-cascaded-s2t-translation
Automatic Speech Recognition • 0.8B • Updated • 6 • 4 -
japanese-asr/en-cascaded-s2t-translation
Automatic Speech Recognition • 0.8B • Updated • 1 • 1
These are the collection of the Bilingual ASR datasets labelled by the whisper-large-v3. The dataset consists of ASR and S2T translation tasks.
-
japanese-asr/en_asr.mls
Viewer • Updated • 10.4M • 848 • 2 -
japanese-asr/whisper_transcriptions.mls
Viewer • Updated • 10.4M • 1.28k • 1 -
japanese-asr/whisper_transcriptions.mls.wer_10.0
Viewer • Updated • 9.33M • 705 • 1 -
japanese-asr/whisper_transcriptions.mls.wer_10.0.vectorized
Viewer • Updated • 7.44M • 2.27k • 1
Japanese ASR Models
-
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-all
0.8B • Updated • 30 • 4 -
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-large
Automatic Speech Recognition • 0.8B • Updated • 30 • 5 -
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-medium
Automatic Speech Recognition • 0.8B • Updated • 6 • 2 -
japanese-asr/distil-whisper-large-v3-ja-reazonspeech-tiny
Automatic Speech Recognition • 0.8B • Updated • 5 • 1
These are the collection of the Japanese ASR datasets labelled by the whisper-large-v3.
-
japanese-asr/whisper_transcriptions.reazonspeech.tiny
Viewer • Updated • 5.32k • 18 -
japanese-asr/whisper_transcriptions.reazonspeech.small
Viewer • Updated • 62k • 36 • 2 -
japanese-asr/whisper_transcriptions.reazonspeech.medium
Viewer • Updated • 619k • 38 -
japanese-asr/whisper_transcriptions.reazonspeech.large
Viewer • Updated • 3.1M • 41
These are the collection of the Japanese ASR datasets labelled by the whisper-large-v3 (WER filter applied).
-
japanese-asr/whisper_transcriptions.reazonspeech.tiny.wer_10.0
Viewer • Updated • 1.77k • 13 -
japanese-asr/whisper_transcriptions.reazonspeech.small.wer_10.0
Viewer • Updated • 20.9k • 9 -
japanese-asr/whisper_transcriptions.reazonspeech.medium.wer_10.0
Viewer • Updated • 209k • 52 -
japanese-asr/whisper_transcriptions.reazonspeech.large.wer_10.0
Viewer • Updated • 1.04M • 33
These are the collection of the Japanese ASR datasets labelled by the whisper-large-v3 (WER filter applied and transformed into logmel feature).
-
japanese-asr/whisper_transcriptions.reazonspeech.tiny.wer_10.0.vectorized
Viewer • Updated • 1.77k • 10 -
japanese-asr/whisper_transcriptions.reazonspeech.small.wer_10.0.vectorized
Viewer • Updated • 3.22k • 33 -
japanese-asr/whisper_transcriptions.reazonspeech.medium.wer_10.0.vectorized
Viewer • Updated • 3.26k • 20 -
japanese-asr/whisper_transcriptions.reazonspeech.large.wer_10.0.vectorized
Viewer • Updated • 3.26k • 47
ASR Evaluation Dataset