Instructions to use Soupis/whisper-base-co with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Soupis/whisper-base-co with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Soupis/whisper-base-co")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Soupis/whisper-base-co") model = AutoModelForSpeechSeq2Seq.from_pretrained("Soupis/whisper-base-co") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
import torch
from transformers import pipeline
device = "cuda:0" if torch.cuda.is_available() else "cpu"
transcribe = pipeline(task="automatic-speech-recognition", model="Enpas/whisper-small-co", chunk_length_s=30, device=device)
transcribe.model.config.forced_decoder_ids = transcribe.tokenizer.get_decoder_prompt_ids(language="am", task="transcribe")
audio = "/content/tr_10000_tr097082.wav"
result = transcribe(audio)
print('Transcription: ', result["text"])
- Downloads last month
- 2