Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Portuguese
whisper
Generated from Trainer
whisper-event
Eval Results (legacy)
Instructions to use pierreguillou/whisper-medium-portuguese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pierreguillou/whisper-medium-portuguese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="pierreguillou/whisper-medium-portuguese")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("pierreguillou/whisper-medium-portuguese") model = AutoModelForSpeechSeq2Seq.from_pretrained("pierreguillou/whisper-medium-portuguese", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.2628188133239746, | |
| "eval_runtime": 4484.4888, | |
| "eval_samples_per_second": 1.938, | |
| "eval_steps_per_second": 0.121, | |
| "eval_wer": 6.598745817992301 | |
| } |