Instructions to use espnet/owsm_v3.1_ebf_small_lowrestriction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/owsm_v3.1_ebf_small_lowrestriction with ESPnet:
import soundfile from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/owsm_v3.1_ebf_small_lowrestriction" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Commit History
14 days ago
-
Send the demo link to one that runs
Verified signaturepyf98/OWSM_v3_demo has been erroring since 2024. The nearest demo that works is espnet/owsm-v4, maintained from egs2/owsm_v4/s2t1/demo in the espnet repository. It serves OWSM v4 rather than this model, so the line says which model a visitor will be trying. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>c1c7591
-
Add a usage example to the model card
Verified signature2c4af4b
-
Upload config.yaml
Verified signature3a0c951 -
Rename old config (which requires flash attention0 to config_flashattn.yaml
Verified signatureSee https://github.com/espnet/espnet/issues/5973b704bdd
-
Update README.md
Verified signature2be4edf
-
Update README.md
Verified signaturecfcc86a
-
add files
a4b693c -
initial commit
Verified signaturef522784