Instructions to use bangla-speech-processing/BanglaASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bangla-speech-processing/BanglaASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bangla-speech-processing/BanglaASR")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("bangla-speech-processing/BanglaASR") model = AutoModelForSpeechSeq2Seq.from_pretrained("bangla-speech-processing/BanglaASR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- d9d69ff1c36f146c65fe25fc960a306c76dfdcd40f9b1537ec4ec13c325be6dd
- Size of remote file:
- 1.93 GB
- SHA256:
- eeaaf64a13d9921605c895799fc0d94dc30c2f1bab5add1dbb0567f465836a64
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.