Change license to CC BY-NC 4.0 and document training data sources
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
pipeline_tag: text-to-audio
|
|
@@ -45,6 +45,17 @@ python -m physwave --condition examples/telephone_static.json --output outputs/t
|
|
| 45 |
See the [code README](https://github.com/lingfengyao/PhysWave#natural-language-input)
|
| 46 |
for Gemini/OpenRouter configuration and more examples.
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
## Citation
|
| 49 |
|
| 50 |
If you use PhysWave in your research, please cite:
|
|
|
|
| 1 |
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
pipeline_tag: text-to-audio
|
|
|
|
| 45 |
See the [code README](https://github.com/lingfengyao/PhysWave#natural-language-input)
|
| 46 |
for Gemini/OpenRouter configuration and more examples.
|
| 47 |
|
| 48 |
+
## License
|
| 49 |
+
|
| 50 |
+
The checkpoints in this repository are released under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/)
|
| 51 |
+
for research and non-commercial use only. They were trained on the PhysWave Dataset, which is rendered from
|
| 52 |
+
AudioCaps, WavCaps (FreeSound, BBC Sound Effects and AudioSet-SL subsets), Clotho, ESC-50 and FSD50K; the terms
|
| 53 |
+
of those sources restrict use to research and non-commercial purposes. Commercial use of the checkpoints or of
|
| 54 |
+
audio generated with them is not permitted.
|
| 55 |
+
|
| 56 |
+
The inference code is released separately under Apache-2.0 (and MIT for the bundled `stable_audio_tools`),
|
| 57 |
+
see the [code repository](https://github.com/lingfengyao/PhysWave).
|
| 58 |
+
|
| 59 |
## Citation
|
| 60 |
|
| 61 |
If you use PhysWave in your research, please cite:
|