Spaces:
Build error
Build error
update colab
Browse files- README.md +3 -2
- audiocraft/models/musicgen.py +1 -1
README.md
CHANGED
@@ -13,7 +13,7 @@ all 4 codebooks in one pass. By introducing a small delay between the codebooks,
|
|
13 |
them in parallel, thus having only 50 auto-regressive steps per second of audio.
|
14 |
Check out our [sample page][musicgen_samples] or test the available demo!
|
15 |
|
16 |
-
<a target="_blank" href="https://colab.research.google.com/drive/
|
17 |
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
18 |
</a>
|
19 |
<a target="_blank" href="https://huggingface.co/spaces/facebook/MusicGen">
|
@@ -41,7 +41,8 @@ We offer a number of way to interact with MusicGen:
|
|
41 |
1. You can play with MusicGen by running the jupyter notebook at [`demo.ipynb`](./demo.ipynb) locally, or use the provided [colab notebook](https://colab.research.google.com/drive/1fxGqfg96RBUvGxZ1XXN07s3DthrKUl4-?usp=sharing).
|
42 |
2. You can use the gradio demo locally by running `python app.py`.
|
43 |
3. A demo is also available on the [`facebook/MusicGen` HuggingFace Space](https://huggingface.co/spaces/facebook/MusicGen) (huge thanks to all the HF team for their support).
|
44 |
-
4. Finally,
|
|
|
45 |
|
46 |
## API
|
47 |
|
|
|
13 |
them in parallel, thus having only 50 auto-regressive steps per second of audio.
|
14 |
Check out our [sample page][musicgen_samples] or test the available demo!
|
15 |
|
16 |
+
<a target="_blank" href="https://colab.research.google.com/drive/1-Xe9NCdIs2sCUbiSmwHXozK6AAhMm7_i?usp=sharing">
|
17 |
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
18 |
</a>
|
19 |
<a target="_blank" href="https://huggingface.co/spaces/facebook/MusicGen">
|
|
|
41 |
1. You can play with MusicGen by running the jupyter notebook at [`demo.ipynb`](./demo.ipynb) locally, or use the provided [colab notebook](https://colab.research.google.com/drive/1fxGqfg96RBUvGxZ1XXN07s3DthrKUl4-?usp=sharing).
|
42 |
2. You can use the gradio demo locally by running `python app.py`.
|
43 |
3. A demo is also available on the [`facebook/MusicGen` HuggingFace Space](https://huggingface.co/spaces/facebook/MusicGen) (huge thanks to all the HF team for their support).
|
44 |
+
4. Finally, you can run the [Gradio demo with a Colab GPU](https://colab.research.google.com/drive/1-Xe9NCdIs2sCUbiSmwHXozK6AAhMm7_i?usp=sharing),
|
45 |
+
as adapted from [@camenduru Colab](https://github.com/camenduru/MusicGen-colab).
|
46 |
|
47 |
## API
|
48 |
|
audiocraft/models/musicgen.py
CHANGED
@@ -88,7 +88,7 @@ class MusicGen:
|
|
88 |
cache_dir = os.environ.get('MUSICGEN_ROOT', None)
|
89 |
compression_model = load_compression_model(name, device=device, cache_dir=cache_dir)
|
90 |
lm = load_lm_model(name, device=device, cache_dir=cache_dir)
|
91 |
-
if name == 'melody'
|
92 |
lm.condition_provider.conditioners['self_wav'].match_len_on_eval = True
|
93 |
|
94 |
return MusicGen(name, compression_model, lm)
|
|
|
88 |
cache_dir = os.environ.get('MUSICGEN_ROOT', None)
|
89 |
compression_model = load_compression_model(name, device=device, cache_dir=cache_dir)
|
90 |
lm = load_lm_model(name, device=device, cache_dir=cache_dir)
|
91 |
+
if name == 'melody':
|
92 |
lm.condition_provider.conditioners['self_wav'].match_len_on_eval = True
|
93 |
|
94 |
return MusicGen(name, compression_model, lm)
|