Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use keess/whisper-model-internal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use keess/whisper-model-internal with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="keess/whisper-model-internal")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("keess/whisper-model-internal") model = AutoModelForSpeechSeq2Seq.from_pretrained("keess/whisper-model-internal", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| from handler import EndpointHandler | |
| from pathlib import Path | |
| p = Path(__file__).with_name('pytorch_model.bin') | |
| filename = p.absolute() | |
| my_handler = EndpointHandler(path=filename) | |
| payload = {"inputs": "contact.wav"} | |
| transcription=my_handler(payload) | |
| print("here is the transcription") | |
| print(transcription) | |