Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Abkhaz
wav2vec2
Generated from Trainer
hf-asr-leaderboard
mozilla-foundation/common_voice_7_0
robust-speech-event
Instructions to use cahya/xls-r-ab-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cahya/xls-r-ab-test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="cahya/xls-r-ab-test")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("cahya/xls-r-ab-test") model = AutoModelForCTC.from_pretrained("cahya/xls-r-ab-test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2840909090909091, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28, | |
| "step": 100, | |
| "total_flos": 3321479416320.0, | |
| "train_loss": 79.240166015625, | |
| "train_runtime": 50.0456, | |
| "train_samples_per_second": 3.996, | |
| "train_steps_per_second": 1.998 | |
| } | |
| ], | |
| "max_steps": 100, | |
| "num_train_epochs": 1, | |
| "total_flos": 3321479416320.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |