Automatic Speech Recognition
Transformers
Safetensors
indic_canary
feature-extraction
speech
audio
asr
multilingual
indic
code-switching
code-mixing
language-identification
canary
fastconformer
quantized
int8
bitsandbytes
custom_code
8-bit precision
Instructions to use ManiKumarAdapala/indic-transcribe-core-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ManiKumarAdapala/indic-transcribe-core-8bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ManiKumarAdapala/indic-transcribe-core-8bit", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ManiKumarAdapala/indic-transcribe-core-8bit", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- f19f17a2bb56793c02471bdfddda86a90aece86deea046967eace13ccb301006
- Size of remote file:
- 1.57 GB
- SHA256:
- b21e78121a85cadd5f7315713cec736bfe151f952eb6c7b0123d08ac600118f0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.