Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Chinese
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use thomas0104/whisper-large-v2-nan-tw-only-char with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thomas0104/whisper-large-v2-nan-tw-only-char with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="thomas0104/whisper-large-v2-nan-tw-only-char")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("thomas0104/whisper-large-v2-nan-tw-only-char") model = AutoModelForMultimodalLM.from_pretrained("thomas0104/whisper-large-v2-nan-tw-only-char") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 6.05, | |
| "train_loss": 0.3433635727233719, | |
| "train_runtime": 5460.4494, | |
| "train_samples_per_second": 1.831, | |
| "train_steps_per_second": 0.916 | |
| } |