Instructions to use soniqo/HTDemucs-Android with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use soniqo/HTDemucs-Android with LiteRT:
# 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
|
Download README.md from soniqo/HTDemucs-Android: direct link, hf CLI and curl.
- Browser
- Download file 3.17 kB
-
https://huggingface.co/soniqo/HTDemucs-Android/resolve/main/README.md
- Command line
-
hf download hf://soniqo/HTDemucs-Android/README.md
-
curl -L -o README.md https://huggingface.co/soniqo/HTDemucs-Android/resolve/main/README.md
3.17 kB
| license: mit | |
| language: [] | |
| base_model: smank/htdemucs-onnx | |
| library_name: tflite | |
| pipeline_tag: audio-to-audio | |
| tags: | |
| - music-source-separation | |
| - onnx | |
| - litert | |
| - android | |
| - opencl | |
| # HTDemucs for Android | |
| FP32 music source separation for 44.1 kHz stereo audio. The model estimates | |
| drums, bass, other instruments and vocals. The runtime can sum the first | |
| three stems to produce an instrumental track. | |
| | File | Format | Size | Use | | |
| | --- | --- | ---: | --- | | |
| | `htdemucs.onnx` | ONNX FP32 | 304,321,552 bytes | ONNX Runtime CPU | | |
| | `separator-fused-norm.tflite` | LiteRT FP32 | 244,796,736 bytes | LiteRT OpenCL GPU | | |
| | `LICENSE` | MIT | | License and attribution | | |
| Both use the same original HTDemucs weights and process 7.8-second windows. | |
| The CPU file exactly matches the pinned upstream ONNX export. The GPU export | |
| changes tensor layouts and how the graph is executed. It uses host-side | |
| framing, inverse STFT and overlap-add. | |
| | SHA-256 | File | | |
| | --- | --- | | |
| | `d2b401f322558cd57d67a752ed7be3fa55178a0626011eda8ac7bb74e17280c0` | `htdemucs.onnx` | | |
| | `3b4aeed464fc0ce5cde49a3404d1cb47ff64a33bc51e88f6de98eaa0fa45d445` | `separator-fused-norm.tflite` | | |
| ## Android measurements | |
| | Samsung Galaxy S23 Ultra, 60-second clip | Elapsed | Real-time factor | | |
| | --- | ---: | ---: | | |
| | LiteRT OpenCL with a warm kernel cache | 20.89 s | 0.348 | | |
| | LiteRT OpenCL with an empty kernel cache | 27.53 s | 0.459 | | |
| These runs used LiteRT 2.3.2 with the model already on the device. Timing | |
| includes model verification and initialization, processing and WAV export. | |
| Warm-run peak sampled process PSS was 1.93 GiB. The five PCM16 outputs | |
| matched the qualified FP32 LiteRT reference across 26.46 million samples. | |
| ## Download | |
| ```sh | |
| hf download soniqo/HTDemucs-Android htdemucs.onnx | |
| hf download soniqo/HTDemucs-Android separator-fused-norm.tflite | |
| ``` | |
| Select one export for the target runtime. The CPU export accepts one | |
| normalized `[1, 2, 343980]` stereo float tensor. The GPU signature also takes | |
| `[672, 4096]` reflection-padded audio frames. Its outputs are a | |
| `[1, 16, 2048, 336]` complex spectrogram representation and a | |
| `[1, 4, 2, 343980]` waveform tensor. Converting the spectrogram to audio | |
| requires the original window and inverse STFT. The runtime adds the waveform | |
| output, reverses input scaling and overlap-adds consecutive windows. | |
| ```python | |
| from huggingface_hub import hf_hub_download | |
| from ai_edge_litert.interpreter import Interpreter | |
| path = hf_hub_download("soniqo/HTDemucs-Android", "separator-fused-norm.tflite") | |
| model = Interpreter(model_path=path) | |
| for tensor in model.get_input_details() + model.get_output_details(): | |
| print(tensor["name"], tensor["shape"], tensor["dtype"]) | |
| ``` | |
| ## Source | |
| The [original Demucs implementation](https://github.com/facebookresearch/demucs) | |
| and [HTDemucs paper](https://arxiv.org/abs/2211.08553) describe the model. | |
| The [pinned ONNX export](https://huggingface.co/smank/htdemucs-onnx/tree/fb1fd25aa6260c253d86bbb4aa26b73aebc79f10) | |
| is the source of both artifacts. See [LiteRT on Android](https://developers.google.com/edge/litert/android) | |
| for runtime integration and [Soniqo Music](https://soniqo.audio/music) for the app. | |