How to use emon-j/Bengali-Whsiper with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="emon-j/Bengali-Whsiper")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("emon-j/Bengali-Whsiper") model = AutoModelForSpeechSeq2Seq.from_pretrained("emon-j/Bengali-Whsiper", device_map="auto")
https://huggingface.co/emon-j/Bengali-Whsiper/resolve/main/tokenizer.json
hf download hf://emon-j/Bengali-Whsiper/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/emon-j/Bengali-Whsiper/resolve/main/tokenizer.json
