Instructions to use levicu/whisat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use levicu/whisat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="levicu/whisat")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("levicu/whisat") model = AutoModelForSpeechSeq2Seq.from_pretrained("levicu/whisat", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
upload pytorch_model.bin
Verified signaturethis doesnt cause problems with loading from_pretrainedafe0051 -
delete seemingly corrupt safetensors model
Verified signature03f3d48 -
model card
Verified signature08df0bd
-
full merged model upload, this time in a single model file (not sharded), remove old sharded versions
Verified signature7678a69
-
remove sharded model files, replaced with single file version
Verified signature87a0738 -
remove sharded model files, replaced with single file version
Verified signature09963a5 -
remove sharded model files, replaced with single file version
Verified signature015b142
-
full merged model upload
Verified signaturea9efe3e -
full merged model upload
Verified signature31b8c3d -
full merged model upload
Verified signature4978ec5 -
initial commit
Verified signature59687a6