Instructions to use espnet/owsm_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/owsm_v3 with ESPnet:
import soundfile from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/owsm_v3" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Download data/token_list/bpe_unigram50000/bpe.model from espnet/owsm_v3: direct link, hf CLI and curl.
- Browser
- Download file 1.04 MB
-
https://huggingface.co/espnet/owsm_v3/resolve/main/data/token_list/bpe_unigram50000/bpe.model
- Command line
-
hf download hf://espnet/owsm_v3/data/token_list/bpe_unigram50000/bpe.model
-
curl -L -o bpe.model https://huggingface.co/espnet/owsm_v3/resolve/main/data/token_list/bpe_unigram50000/bpe.model
1.04 MB
- Xet hash:
- 548750741ec3b1e5d83080968c44614739bbcc3d2f78280a5a271f31645d6122
- Size of remote file:
- 1.04 MB
- SHA256:
- 623b8767f80bd60036d8c207b96b25306a8181aa5a702cdac2bf5e90348da174
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.