Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Uzbek
wav2vec2
pretraining
mozilla-foundation/common_voice_10_0
Generated from Trainer
Instructions to use vodiylik/xls-r-uzbek-cv10-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vodiylik/xls-r-uzbek-cv10-full with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="vodiylik/xls-r-uzbek-cv10-full")# Load model directly from transformers import AutoProcessor, AutoModelForPreTraining processor = AutoProcessor.from_pretrained("vodiylik/xls-r-uzbek-cv10-full") model = AutoModelForPreTraining.from_pretrained("vodiylik/xls-r-uzbek-cv10-full", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 100.0, | |
| "eval_cer": 0.05127812810788953, | |
| "eval_loss": 0.2491369992494583, | |
| "eval_runtime": 179.6938, | |
| "eval_samples": 5785, | |
| "eval_samples_per_second": 32.194, | |
| "eval_steps_per_second": 4.029, | |
| "eval_wer": 0.25884590640821237, | |
| "train_loss": 0.0, | |
| "train_runtime": 32.0497, | |
| "train_samples": 23538, | |
| "train_samples_per_second": 73442.278, | |
| "train_steps_per_second": 2293.316 | |
| } |