Instructions to use rosyvs/whisat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rosyvs/whisat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="rosyvs/whisat")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("rosyvs/whisat") model = AutoModelForSpeechSeq2Seq.from_pretrained("rosyvs/whisat", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Upload 7 files
Verified signatureconfog fiels for whisper large-v2b2b36cc -
Create generation_config.json
Verified signatureadded generation_config5f1933d
-
upload adapter_model.bin to main level
Verified signatureefa06cf
-
md nice
Verified signature91d1a17 -
block nice
Verified signature6a9787b -
add data manifest
Verified signaturec593553 -
new READMe, tidy up main and add hparams
rosyvse404b97
-
add links to isatasr repo to readme
f60eaa1
-
add config files
9667a74 -
add description for model options
4db98ee -
example usage
d0dded1 -
main.py created - contains code for transcription
7c2d6fa -
update readme
3c0cc82 -
upload model fils for whisat-1.2
ba5e2c9
-
Create README.md
a5466d4 -
initial commit
7f49497