Instructions to use nyralabs/CrisperWhisper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nyralabs/CrisperWhisper with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nyralabs/CrisperWhisper")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("nyralabs/CrisperWhisper") model = AutoModelForSpeechSeq2Seq.from_pretrained("nyralabs/CrisperWhisper") - Notebooks
- Google Colab
- Kaggle
IndexError: list index out of range
#3
by MatBar99 - opened
Hi, I try to run repo using sample code provided. Unfortunetely, I get this error:
Traceback (most recent call last):
hf_pipeline_output = pipe(sample)
return super().__call__(inputs, **kwargs)
return next(
processed = self.infer(item, **self.params)
text, optional = self.tokenizer._decode_asr(
return _decode_asr(
start_time = round(token_timestamps[i] + time_offset, 2)
I'm using conda and I installed all needed packages using tutorial provided here: https://github.com/nyrahealth/CrisperWhisper
could you checkout this issue and see if this solves your problem: