Automatic Speech Recognition
Transformers
Safetensors
Bhojpuri
Hindi
whisper
bhojpuri
indic
low-resource
Eval Results (legacy)
Instructions to use Aditya109/whisper-small-bhojpuri-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Aditya109/whisper-small-bhojpuri-merged with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Aditya109/whisper-small-bhojpuri-merged")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Aditya109/whisper-small-bhojpuri-merged") model = AutoModelForSpeechSeq2Seq.from_pretrained("Aditya109/whisper-small-bhojpuri-merged", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 3867b1eb543236e9bc9bc7517355521f2a6fcb670f5ab8bd628f71465a77f8f7
- Size of remote file:
- 967 MB
- SHA256:
- 72a4b8e039806faac0b1c4805c06b27a403ec58292ebebf35888ab75aa249d7e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.