Instructions to use qmeeus/la-whisper-small-covost2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qmeeus/la-whisper-small-covost2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="qmeeus/la-whisper-small-covost2")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("qmeeus/la-whisper-small-covost2") model = AutoModelForSpeechSeq2Seq.from_pretrained("qmeeus/la-whisper-small-covost2") - Notebooks
- Google Colab
- Kaggle
File size: 238 Bytes
8a720d6 | 1 2 3 4 5 6 7 8 9 | {
"epoch": 4.5,
"eval_loss": 2.1667492389678955,
"eval_runtime": 6455.0764,
"eval_sacrebleu": 118.26401526639184,
"eval_samples_per_second": 0.526,
"eval_steps_per_second": 0.263,
"eval_wer": 686.689662169017
} |