Instructions to use biodatlab/whisper-th-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use biodatlab/whisper-th-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="biodatlab/whisper-th-medium")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("biodatlab/whisper-th-medium") model = AutoModelForSpeechSeq2Seq.from_pretrained("biodatlab/whisper-th-medium") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 0.82, | |
| "train_loss": 0.18710677490234376, | |
| "train_runtime": 35654.5907, | |
| "train_samples": 194401, | |
| "train_samples_per_second": 4.488, | |
| "train_steps_per_second": 0.28 | |
| } |