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