How to use BELLE-2/Belle-whisper-large-v2-zh with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="BELLE-2/Belle-whisper-large-v2-zh")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("BELLE-2/Belle-whisper-large-v2-zh") model = AutoModelForSpeechSeq2Seq.from_pretrained("BELLE-2/Belle-whisper-large-v2-zh", device_map="auto")
I tried using the following code, but it doesn't work.transcriber.model.config.forced_decoder_ids = ( transcriber.tokenizer.get_decoder_prompt_ids( language="zh", task="transcribe", no_timestamps=False ))
· Sign up or log in to comment
