Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
mozilla-foundation/common_voice_8_0
Generated from Trainer
pa-IN
robust-speech-event
model_for_talk
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use DrishtiSharma/wav2vec2-xls-r-300m-pa-IN-r5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DrishtiSharma/wav2vec2-xls-r-300m-pa-IN-r5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="DrishtiSharma/wav2vec2-xls-r-300m-pa-IN-r5")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("DrishtiSharma/wav2vec2-xls-r-300m-pa-IN-r5") model = AutoModelForCTC.from_pretrained("DrishtiSharma/wav2vec2-xls-r-300m-pa-IN-r5") - Notebooks
- Google Colab
- Kaggle
| {"¤": 1, "ਂ": 2, "ਅ": 3, "ਆ": 4, "ਇ": 5, "ਈ": 6, "ਉ": 7, "ਊ": 8, "ਏ": 9, "ਐ": 10, "ਓ": 11, "ਔ": 12, "ਕ": 13, "ਖ": 14, "ਗ": 15, "ਘ": 16, "ਚ": 17, "ਛ": 18, "ਜ": 19, "ਝ": 20, "ਟ": 21, "ਠ": 22, "ਡ": 23, "ਢ": 24, "ਣ": 25, "ਤ": 26, "ਥ": 27, "ਦ": 28, "ਧ": 29, "ਨ": 30, "ਪ": 31, "ਫ": 32, "ਬ": 33, "ਭ": 34, "ਮ": 35, "ਯ": 36, "ਰ": 37, "ਲ": 38, "ਲ਼": 39, "ਵ": 40, "ਸ਼": 41, "ਸ": 42, "ਹ": 43, "਼": 44, "ਾ": 45, "ਿ": 46, "ੀ": 47, "ੁ": 48, "ੂ": 49, "ੇ": 50, "ੈ": 51, "ੋ": 52, "ੌ": 53, "੍": 54, "ਖ਼": 55, "ਗ਼": 56, "ਜ਼": 57, "ੜ": 58, "ਫ਼": 59, "ੰ": 60, "ੱ": 61, "|": 0, "[UNK]": 62, "[PAD]": 63} |