Automatic Speech Recognition
NeMo
Safetensors
indic_canary
speech
audio
asr
multilingual
indic
code-switching
code-mixing
romanization
transliteration
language-identification
canary
fastconformer
custom_code
Instructions to use spark-ux/indic-transcribe-flex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use spark-ux/indic-transcribe-flex with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("spark-ux/indic-transcribe-flex") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- c368aab2c7b08e6118b1259020c9243d0fa7e5adc5e152c20cccc794c19fae6e
- Size of remote file:
- 342 kB
- SHA256:
- caac4b6023fe90422bd2658f89e18b9eda53b78bb54be85a212ebba480dc29bd
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.