Downloads · 30 days
0
bharatgenai/Shrutam-HindiASR-1.0
Shrutam-HindiASR-1.0 is a automatic speech recognition model from bharatgenai. Use it when you need speech turned into text.
Instructions for ESPNet Inference Environment Setup
Downloads · 30 days
0
Access
Public
Updated Jan 1, 2026
Repo size
107 MB
Likes
7
Public
Click a slice to open those files.
.pth107 MB · 100%
From the Hugging Face model README
Instructions for ESPNet Inference Environment Setup
Execute the following commands to set up the inference environment:
apt update && apt install git-lfs
git clone https://huggingface.co/bharatgenai/Shrutam-HindiASR-1.0
python3 -m venv ASR_infer
source ./ASR_infer/bin/activate
pip install git+https://github.com/Adhikari-Ashutosh/espnet.git@lazy-infer
Navigate to the model directory and run inference:
cd Shrutam-HindiASR-1.0
python3 inference.py --audio <path-to-audio-file>
python3 inference.py --audio test.wav
Note: The custom ESPNet branch (lazy-infer) includes the necessary modifications for RNNTLoss compatibility.