Instructions to use emon1521/wav2vec2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use emon1521/wav2vec2-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="emon1521/wav2vec2-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("emon1521/wav2vec2-base") model = AutoModelForCTC.from_pretrained("emon1521/wav2vec2-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download vocab.json from emon1521/wav2vec2-base: direct link, hf CLI and curl.
- Browser
- Download file 268 Bytes
-
https://huggingface.co/emon1521/wav2vec2-base/resolve/main/vocab.json
- Command line
-
hf download hf://emon1521/wav2vec2-base/vocab.json
-
curl -L -o vocab.json https://huggingface.co/emon1521/wav2vec2-base/resolve/main/vocab.json
268 Bytes
| {"h": 0, "w": 1, "a": 2, "d": 3, "c": 4, "x": 5, "r": 6, "i": 7, "f": 8, "b": 9, "q": 10, "s": 11, "t": 12, "l": 13, "z": 15, "y": 16, "m": 17, "u": 18, "k": 19, "v": 20, "e": 21, "p": 22, "o": 23, "j": 24, "n": 25, "g": 26, "'": 27, "|": 14, "[UNK]": 28, "[PAD]": 29} |