How to use KBLab/kb-whisper-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="KBLab/kb-whisper-tiny")
# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("KBLab/kb-whisper-tiny") model = AutoModelForSpeechSeq2Seq.from_pretrained("KBLab/kb-whisper-tiny", device_map="auto")
https://huggingface.co/KBLab/kb-whisper-tiny/resolve/refs%2Fpr%2F1/tokenizer.json
hf download hf://KBLab/kb-whisper-tiny@refs/pr/1/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/KBLab/kb-whisper-tiny/resolve/refs%2Fpr%2F1/tokenizer.json
