-
Update README.md
-
Update README: ONNX -> QNN in description
dev-ansh-r +1: Claude Opus 4.6 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> -
Add WIP note to README
dev-ansh-r +1: Claude Opus 4.6 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> -
Track .raw and .wav with LFS, add audio embed to README
dev-ansh-r +1: Claude Opus 4.6 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> -
Merge HF remote, keep local versions
-
Add HF model card metadata and audio sample embed
dev-ansh-r +1: Claude Opus 4.6 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> -
gitmodules updated
-
Initial commit: Supertonic2 QNN quantized TTS pipeline
dev-ansh-r +1: Claude Opus 4.6 Add complete Qualcomm QNN-optimized TTS pipeline including:
- ONNX models (text encoder, vector estimator, vocoder, duration predictor)
- QNN HTP compiled models and shared libraries
- Calibration data for quantization
- Inference scripts and pipeline runner
- Architecture documentation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> -
initial commit