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