Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Japanese
wav2vec2
common-voice
hf-asr-leaderboard
robust-speech-event
Eval Results (legacy)
Instructions to use vumichien/wav2vec2-xls-r-1b-japanese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vumichien/wav2vec2-xls-r-1b-japanese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="vumichien/wav2vec2-xls-r-1b-japanese")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("vumichien/wav2vec2-xls-r-1b-japanese") model = AutoModelForCTC.from_pretrained("vumichien/wav2vec2-xls-r-1b-japanese", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| {"v": 0, "ใ": 1, "ใ": 2, "ใ": 3, "ใ": 4, "n": 5, "ใต": 6, "ใ": 7, "ใ": 8, "ใฟ": 9, "ใพ": 10, "ใ": 11, "w": 12, "ใ": 13, "ใ": 14, "ใฎ": 15, "ใฆ": 16, "ใฉ": 17, "q": 18, "ใถ": 19, "ใ ": 20, "ใ": 21, "ใ": 22, "ใ": 23, "ใน": 24, "e": 25, "ใฑ": 26, "ใ": 27, "c": 28, "ใ": 29, "ใ": 30, "ใ": 31, "ใข": 32, "ใ": 33, "ใผ": 34, "t": 35, "l": 36, "ใ": 37, "p": 38, "f": 39, "ใจ": 40, "ใ": 41, "ใฐ": 42, "ใฝ": 43, "ใผ": 44, "ใ": 45, "ใ": 46, "ใช": 47, "ใค": 48, "ใ": 49, "ใ": 50, "ใธ": 51, "ใฏ": 52, "ใญ": 53, "ใ": 54, "ใบ": 55, "ใป": 56, "ใ": 57, "y": 58, "g": 59, "ใ": 60, "ใฒ": 61, "ใ": 62, "&": 63, "ใ": 64, "m": 65, "ใ": 66, "ใ": 67, "o": 68, "z": 70, "ใ": 71, "ใ": 72, "ใ ": 73, "ใก": 74, "ใ": 75, "ใ ": 76, "ใฃ": 77, "ใ": 78, "ใ": 79, "ใ": 80, "ใ": 81, "ใ": 82, "k": 83, "a": 84, "ใ": 85, "ใง": 86, "u": 87, "ใฅ": 88, "b": 89, "ใ": 90, "ใ ": 91, "ใ": 92, "d": 93, "ใ": 94, "ใ": 95, "ใ": 96, "็นซ": 97, "ใฌ": 98, "ใณ": 99, "ใซ": 100, "h": 101, "ใ": 102, "r": 103, "\\": 104, "i": 105, "ใด": 106, "ใ": 107, "x": 108, "ใท": 109, "j": 110, "ใ": 111, "s": 112, "ใ": 113, "|": 69, "[UNK]": 114, "[PAD]": 115} |