Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
English
wav2vec2
voxpopuli
google/xtreme_s
Generated from Trainer
Instructions to use anton-l/xtreme_s_xlsr_300m_voxpopuli_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anton-l/xtreme_s_xlsr_300m_voxpopuli_en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="anton-l/xtreme_s_xlsr_300m_voxpopuli_en")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("anton-l/xtreme_s_xlsr_300m_voxpopuli_en") model = AutoModelForCTC.from_pretrained("anton-l/xtreme_s_xlsr_300m_voxpopuli_en", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 10.0, | |
| "epoch_cs": 10.0, | |
| "epoch_de": 10.0, | |
| "epoch_en": 10.0, | |
| "epoch_es": 10.0, | |
| "epoch_fi": 10.0, | |
| "epoch_fr": 10.0, | |
| "epoch_hr": 10.0, | |
| "epoch_hu": 10.0, | |
| "epoch_it": 10.0, | |
| "epoch_nl": 10.0, | |
| "epoch_pl": 10.0, | |
| "epoch_ro": 10.0, | |
| "epoch_sk": 10.0, | |
| "epoch_sl": 10.0, | |
| "eval_cer": 0.09657029192146015, | |
| "eval_cer_en": 0.09657029192146015, | |
| "eval_loss": 0.3126685321331024, | |
| "eval_loss_en": 0.3126685321331024, | |
| "eval_runtime": 3.8804071428571434, | |
| "eval_samples_per_second": 2.428785714285714, | |
| "eval_steps_per_second": 0.3045714285714286, | |
| "eval_wer": 0.15493465525011266, | |
| "eval_wer_en": 0.15493465525011266, | |
| "predict_samples": 1842 | |
| } |