Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Chinese
whisper
whisper-event
Generated from Trainer
Instructions to use lorenzoncina/whisper-medium-zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lorenzoncina/whisper-medium-zh with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="lorenzoncina/whisper-medium-zh")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("lorenzoncina/whisper-medium-zh") model = AutoModelForSpeechSeq2Seq.from_pretrained("lorenzoncina/whisper-medium-zh") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 7.07, | |
| "eval_cer": 10.978180052967598, | |
| "eval_loss": 0.32260650396347046, | |
| "eval_runtime": 2350.9544, | |
| "eval_samples_per_second": 4.501, | |
| "eval_steps_per_second": 0.563, | |
| "train_loss": 0.14908174896221607, | |
| "train_runtime": 62798.3056, | |
| "train_samples_per_second": 2.548, | |
| "train_steps_per_second": 0.159 | |
| } |