Automatic Speech Recognition
Transformers
PyTorch
Abkhaz
wav2vec2
mozilla-foundation/common_voice_7_0
Generated from Trainer
Instructions to use deepdml/output with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepdml/output with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="deepdml/output")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("deepdml/output") model = AutoModelForCTC.from_pretrained("deepdml/output", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 0.03, | |
| "eval_loss": 156.87892150878906, | |
| "eval_runtime": 10.4702, | |
| "eval_samples": 301, | |
| "eval_samples_per_second": 28.748, | |
| "eval_steps_per_second": 3.629, | |
| "eval_wer": 1.3456221198156681, | |
| "train_loss": 94.46571044921875, | |
| "train_runtime": 11.7935, | |
| "train_samples": 704, | |
| "train_samples_per_second": 1.696, | |
| "train_steps_per_second": 0.848 | |
| } |