Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Uyghur
wav2vec2
Generated from Trainer
hf-asr-leaderboard
mozilla-foundation/common_voice_8_0
robust-speech-event
Eval Results (legacy)
Instructions to use lucio/xls-r-uyghur-cv8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lucio/xls-r-uyghur-cv8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="lucio/xls-r-uyghur-cv8")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("lucio/xls-r-uyghur-cv8") model = AutoModelForCTC.from_pretrained("lucio/xls-r-uyghur-cv8") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 100.0, | |
| "eval_loss": 0.20362737774848938, | |
| "eval_runtime": 146.0593, | |
| "eval_samples": 2744, | |
| "eval_samples_per_second": 18.787, | |
| "eval_steps_per_second": 2.348, | |
| "eval_wer": 0.2976980458560249, | |
| "train_loss": 1.1418190615227881, | |
| "train_runtime": 52190.9896, | |
| "train_samples": 6034, | |
| "train_samples_per_second": 11.561, | |
| "train_steps_per_second": 0.36 | |
| } |