Automatic Speech Recognition
ESPnet
multilingual
audio
speech-translation
language-identification
Eval Results
Instructions to use espnet/owsm_ctc_v3.2_ft_1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/owsm_ctc_v3.2_ft_1B with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/owsm_ctc_v3.2_ft_1B" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Commit History
Add Open ASR Leaderboard evaluation results (#1) d9562e0
Update README.md b7343db verified
Update README.md a58c2f2 verified
Update README.md 920e145 verified
Update README.md 3719821 verified
Update README.md 7c2420b verified
Update README.md b705079 verified
Update README.md e1f251b verified
Update README.md b794c0c verified
Update README.md c2aaf6e verified
Update README.md 2a993fb verified
Update README.md c637f39 verified
Update README.md 2ac79a3 verified
Update README.md e91956e verified
add files b0add0d
Yifan Peng commited on