Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Eval Results (legacy)
Instructions to use dmusingu/luganda_wav2vec2_ctc_train_clean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmusingu/luganda_wav2vec2_ctc_train_clean with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="dmusingu/luganda_wav2vec2_ctc_train_clean")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("dmusingu/luganda_wav2vec2_ctc_train_clean") model = AutoModelForCTC.from_pretrained("dmusingu/luganda_wav2vec2_ctc_train_clean") - Notebooks
- Google Colab
- Kaggle
| { | |
| "'": 1, | |
| "(": 10, | |
| ")": 23, | |
| "[PAD]": 32, | |
| "[UNK]": 31, | |
| "a": 28, | |
| "b": 4, | |
| "c": 0, | |
| "d": 8, | |
| "e": 26, | |
| "f": 21, | |
| "g": 3, | |
| "h": 17, | |
| "i": 15, | |
| "j": 27, | |
| "k": 18, | |
| "l": 19, | |
| "m": 25, | |
| "n": 16, | |
| "o": 9, | |
| "p": 29, | |
| "r": 11, | |
| "s": 22, | |
| "t": 13, | |
| "u": 20, | |
| "v": 12, | |
| "w": 5, | |
| "x": 30, | |
| "y": 2, | |
| "z": 24, | |
| "|": 14, | |
| "‘": 6, | |
| "’": 7 | |
| } | |