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
How to set the language in the Inference API headers?
#2
by chameleon-lizard - opened
I want to transcribe Russian speech into Russian text, but the resulting text from the Inference API is in English. Any ideas how to provide the language to the model?
I am looking for the something similar, were you able to get it?
Found the answer for it we just have to pass the language parameter as mentioned below
whisper_small_model.transcribe(f"/content/Chai_Bisket_Stories_16-08-2021_14-17/{file_name}",language="Russian")
This comment has been hidden
How to add this config in JavaScript or Curl?