Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use openai/whisper-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-small")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-small") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-small") - Notebooks
- Google Colab
- Kaggle
TFLite Model Translates Non-English Transcription Automatically
#44
by rabyunghwa - opened
Hello! Very good model! However, I've found out that the converted TFLite model somehow automatically translates a non-English transcription into English. How do I fix this? I want the output text to be in the original non-English language. The TF model works as expected so I'm assuming this has to do with the TFLite model only.
This comment has been hidden (marked as Off-Topic)