Automatic Speech Recognition
Transformers
Safetensors
indic_canary
feature-extraction
speech
audio
asr
multilingual
indic
code-switching
code-mixing
language-identification
canary
fastconformer
custom_code
Instructions to use spark-ux/indic-transcribe-core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use spark-ux/indic-transcribe-core with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="spark-ux/indic-transcribe-core", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("spark-ux/indic-transcribe-core", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token_id": 4, | |
| "decoder_start_token_id": 7, | |
| "do_sample": false, | |
| "eos_token_id": [ | |
| 3, | |
| 2 | |
| ], | |
| "max_length": 1024, | |
| "num_beams": 1, | |
| "pad_token_id": 2 | |
| } |