Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results (legacy)
Instructions to use golesheed/wav2vec2-large-xls-r-1b-cv-13-elderly-frisian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use golesheed/wav2vec2-large-xls-r-1b-cv-13-elderly-frisian with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="golesheed/wav2vec2-large-xls-r-1b-cv-13-elderly-frisian")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("golesheed/wav2vec2-large-xls-r-1b-cv-13-elderly-frisian") model = AutoModelForCTC.from_pretrained("golesheed/wav2vec2-large-xls-r-1b-cv-13-elderly-frisian", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "'": 7, | |
| "[PAD]": 27, | |
| "[UNK]": 26, | |
| "a": 19, | |
| "b": 14, | |
| "c": 20, | |
| "d": 6, | |
| "e": 3, | |
| "f": 11, | |
| "g": 2, | |
| "h": 21, | |
| "i": 1, | |
| "j": 16, | |
| "k": 25, | |
| "l": 22, | |
| "m": 10, | |
| "n": 4, | |
| "o": 15, | |
| "p": 5, | |
| "r": 24, | |
| "s": 8, | |
| "t": 18, | |
| "u": 12, | |
| "v": 17, | |
| "w": 9, | |
| "y": 23, | |
| "z": 0, | |
| "|": 13 | |
| } | |