Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results (legacy)
Instructions to use davidilag/wav2vec2-xls-r-1b-danish-12h-6k-steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use davidilag/wav2vec2-xls-r-1b-danish-12h-6k-steps with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="davidilag/wav2vec2-xls-r-1b-danish-12h-6k-steps")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("davidilag/wav2vec2-xls-r-1b-danish-12h-6k-steps") model = AutoModelForCTC.from_pretrained("davidilag/wav2vec2-xls-r-1b-danish-12h-6k-steps") - Notebooks
- Google Colab
- Kaggle
| { | |
| "'": 31, | |
| "[PAD]": 39, | |
| "[UNK]": 38, | |
| "a": 22, | |
| "b": 23, | |
| "c": 16, | |
| "d": 33, | |
| "e": 21, | |
| "f": 34, | |
| "g": 17, | |
| "h": 30, | |
| "i": 26, | |
| "j": 29, | |
| "k": 32, | |
| "l": 5, | |
| "m": 11, | |
| "n": 4, | |
| "o": 27, | |
| "p": 12, | |
| "q": 13, | |
| "r": 1, | |
| "s": 9, | |
| "t": 6, | |
| "u": 28, | |
| "v": 15, | |
| "w": 8, | |
| "x": 7, | |
| "y": 20, | |
| "z": 14, | |
| "|": 2, | |
| "«": 0, | |
| "»": 36, | |
| "å": 24, | |
| "æ": 37, | |
| "é": 3, | |
| "í": 18, | |
| "ó": 35, | |
| "ø": 19, | |
| "–": 25, | |
| "—": 10 | |
| } | |