Instructions to use bharatgenai/sooktam2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bharatgenai/sooktam2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="bharatgenai/sooktam2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bharatgenai/sooktam2", trust_remote_code=True, dtype="auto") - F5-TTS
How to use bharatgenai/sooktam2 with F5-TTS:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| set -e | |
| # apt update | |
| # apt-get install libavformat-dev libavdevice-dev -y | |
| # if gpu is available | |
| if [ -n "$(lspci | grep NVIDIA)" ]; then | |
| apt-get install libcudnn9-cuda-12 -y | |
| fi | |
| pip install torch==2.6.0 torchaudio==2.6.0 torchvision==0.21.0 transformers==4.41.2 huggingface-hub==0.24.7 indic-nlp-library==0.92 | |
| echo "Installing dependencies for prepare_cls_version.py..." | |
| pip install \ | |
| datasets==4.5.0 \ | |
| tqdm \ | |
| indo-arabic-transliteration==0.1.5 \ | |
| indic-unified-parser==1.0.6 \ | |
| indic-numtowords==1.1.0 \ | |
| indic-nlp-library==0.92 \ | |
| git+https://github.com/libindic/indic-trans.git@0287fa62289968f0ce06cbe2df61cfadf4088c75 \ | |
| urduhack==1.1.1 \ | |
| keras==2.15.0 \ | |
| tensorflow==2.15.0 \ | |
| tensorflow-addons==0.23.0 \ | |
| fastapi==0.128.7 \ | |
| uvicorn==0.40.0 | |
| pip install indic_unified_parser==1.0.6 indo-arabic-transliteration==0.1.5 indic-numtowords==1.1.0 | |
| pip install click==8.0.1 | |
| pip install -e . --no-cache-dir | |