|
|
--- |
|
|
license: apache-2.0 |
|
|
pipeline_tag: audio-to-audio |
|
|
tags: |
|
|
- comfy |
|
|
- comfyui |
|
|
- audio2audio |
|
|
- audio-to-audio |
|
|
- audio-upscale |
|
|
- audiosuperresolution |
|
|
--- |
|
|
# Custom Node for ComfyUI |
|
|
|
|
|
https://github.com/Saganaki22/ComfyUI-NovaSR |
|
|
|
|
|
 |
|
|
|
|
|
## NovaSR: Pushing the Limits of Extreme Efficiency in Audio Super-Resolution |
|
|
|
|
|
This is the model for NovaSR, a tiny 50kb audio upsampling model that upscales muffled 16khz audio into clear and crisp 48khz audio at speeds from 100-3500x realtime. |
|
|
|
|
|
### Audio Samples |
|
|
|
|
|
**Before Processing (16kHz):** |
|
|
<audio controls> |
|
|
<source src="https://huggingface.co/drbaph/NovaSR/resolve/main/samples/speech_sample_before.mp3" type="audio/mpeg"> |
|
|
Your browser does not support the audio element. |
|
|
</audio> |
|
|
|
|
|
**After Processing (48kHz):** |
|
|
<audio controls> |
|
|
<source src="https://huggingface.co/drbaph/NovaSR/resolve/main/samples/speech_sample_after.mp3" type="audio/mpeg"> |
|
|
Your browser does not support the audio element. |
|
|
</audio> |
|
|
|
|
|
 |
|
|
|
|
|
### Details |
|
|
|
|
|
* **Model Size:** 52kb for pytorch version |
|
|
* **Input Rate:** 16kHz |
|
|
* **Output Rate:** 48kHz |
|
|
* **Inference Speed:** 300-3500x realtime depending on gpu |
|
|
* **Mono** |
|
|
|
|
|
## Comparisons |
|
|
|
|
|
Comparisons were done on A100 gpu. Higher realtime means faster processing speeds. |
|
|
Comparison on CPU are coming soon. |
|
|
|
|
|
| Model | Speed (Real-Time) | Model Size | |
|
|
| :------------ | :---------------- | :--------- | |
|
|
| **NovaSR** | **3600x realtime** | **~52 KB** | |
|
|
| FlowHigh | 20x realtime | ~450 MB | |
|
|
| FlashSR | 14x realtime | ~1000 MB | |
|
|
| AudioSR | 0.6x realtime | ~6000 MB | |
|
|
|
|
|
## Usage |
|
|
|
|
|
Please check out the github repo for usage: https://github.com/Saganaki22/ComfyUI-NovaSR |
|
|
|
|
|
Original Repo: https://github.com/ysharma3501/NovaSR |
|
|
|
|
|
If you find the model/code helpful, stars or likes would be appreciated. |
|
|
|
|
|
Thank you. |