Automatic Speech Recognition
Transformers
PyTorch
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results
Instructions to use openai/whisper-large-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large-v3") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large-v3", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Hallucination / repetition
#19
by persundstrom - opened
Hello, any tips on how to deal with hallucination?
I assume the repetition is due to silence.
same as you
I would recommend enabling timestamp prediction (as done in the code-snippet: https://huggingface.co/openai/whisper-large-v3#usage). You can also tune the chunk_length_s and see if a lower value helps reduce hallucinations (as it does for Distil-Whisper for example).