Automatic Speech Recognition
Transformers
Safetensors
wav2vec2-bert
Generated from Trainer
Eval Results (legacy)
Instructions to use Ber5h/wav2vec-bert-2.0-ulch-try with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ber5h/wav2vec-bert-2.0-ulch-try with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Ber5h/wav2vec-bert-2.0-ulch-try")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Ber5h/wav2vec-bert-2.0-ulch-try") model = AutoModelForCTC.from_pretrained("Ber5h/wav2vec-bert-2.0-ulch-try", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "feature_extractor_type": "SeamlessM4TFeatureExtractor", | |
| "feature_size": 80, | |
| "num_mel_bins": 80, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "stride": 2 | |
| } | |