Instructions to use scasutt/wav2vec2-base_toy_train_data with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use scasutt/wav2vec2-base_toy_train_data with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="scasutt/wav2vec2-base_toy_train_data")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("scasutt/wav2vec2-base_toy_train_data") model = AutoModelForCTC.from_pretrained("scasutt/wav2vec2-base_toy_train_data") - Notebooks
- Google Colab
- Kaggle
| {"q": 0, "a": 1, "t": 2, "y": 3, "k": 4, "h": 5, "c": 6, "i": 7, "z": 8, "m": 9, "o": 10, "e": 11, "x": 12, "f": 13, "b": 14, "l": 15, "v": 16, "n": 18, "ü": 19, "d": 20, "p": 21, "j": 22, "ö": 23, "w": 24, "ä": 25, "s": 26, "r": 27, "g": 28, "u": 29, "|": 17, "[UNK]": 30, "[PAD]": 31} |