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