Spaces:
Running on Zero
Running on Zero
prismaudio-project commited on
Commit Β·
8031e67
1
Parent(s): 7568a1a
init
Browse filesThis view is limited to 50 files because it contains too many changes. Β See raw diff
- {ThinkSound β PrismAudio}/__init__.py +0 -0
- {ThinkSound β PrismAudio}/configs/model_configs/prismaudio.json +0 -0
- {ThinkSound β PrismAudio}/configs/model_configs/stable_audio_2_0_vae.json +0 -0
- {ThinkSound β PrismAudio}/configs/model_configs/thinksound.json +0 -0
- {ThinkSound β PrismAudio}/configs/multimodal_dataset_demo.json +0 -0
- {ThinkSound β PrismAudio}/configs/multimodal_dataset_demo_prismaudio.json +6 -6
- {ThinkSound β PrismAudio}/data/__init__.py +0 -0
- {ThinkSound β PrismAudio}/data/datamodule.py +0 -0
- {ThinkSound β PrismAudio}/data/dataset.py +0 -0
- {ThinkSound β PrismAudio}/data/utils.py +0 -0
- {ThinkSound β PrismAudio}/inference/__init__.py +0 -0
- {ThinkSound β PrismAudio}/inference/generation.py +0 -0
- {ThinkSound β PrismAudio}/inference/sampling.py +0 -0
- {ThinkSound β PrismAudio}/inference/utils.py +0 -0
- {ThinkSound β PrismAudio}/interface/__init__.py +0 -0
- {ThinkSound β PrismAudio}/interface/aeiou.py +0 -0
- {ThinkSound β PrismAudio}/interface/gradio.py +0 -0
- {ThinkSound β PrismAudio}/models/__init__.py +0 -0
- {ThinkSound β PrismAudio}/models/adp.py +0 -0
- {ThinkSound β PrismAudio}/models/autoencoders.py +0 -0
- {ThinkSound β PrismAudio}/models/blocks.py +0 -0
- {ThinkSound β PrismAudio}/models/bottleneck.py +0 -0
- {ThinkSound β PrismAudio}/models/codebook_patterns.py +0 -0
- {ThinkSound β PrismAudio}/models/conditioners.py +0 -0
- {ThinkSound β PrismAudio}/models/diffusion.py +0 -0
- {ThinkSound β PrismAudio}/models/diffusion_prior.py +0 -0
- {ThinkSound β PrismAudio}/models/discriminators.py +0 -0
- {ThinkSound β PrismAudio}/models/dit (1).py +0 -0
- {ThinkSound β PrismAudio}/models/dit.py +0 -0
- {ThinkSound β PrismAudio}/models/factory.py +0 -0
- {ThinkSound β PrismAudio}/models/lm.py +0 -0
- {ThinkSound β PrismAudio}/models/lm_backbone.py +0 -0
- {ThinkSound β PrismAudio}/models/lm_continuous.py +0 -0
- {ThinkSound β PrismAudio}/models/local_attention.py +0 -0
- {ThinkSound β PrismAudio}/models/meta_queries/__init__.py +0 -0
- {ThinkSound β PrismAudio}/models/meta_queries/metaquery.py +0 -0
- {ThinkSound β PrismAudio}/models/meta_queries/model.py +0 -0
- {ThinkSound β PrismAudio}/models/meta_queries/models/__init__.py +0 -0
- {ThinkSound β PrismAudio}/models/meta_queries/models/process_audio_info.py +0 -0
- {ThinkSound β PrismAudio}/models/meta_queries/models/qwen25VL.py +0 -0
- {ThinkSound β PrismAudio}/models/meta_queries/models/qwen25omni.py +0 -0
- {ThinkSound β PrismAudio}/models/meta_queries/transformer_encoder.py +0 -0
- {ThinkSound β PrismAudio}/models/mmdit.py +0 -0
- {ThinkSound β PrismAudio}/models/mmmodules/__init__.py +0 -0
- {ThinkSound β PrismAudio}/models/mmmodules/ext/__init__.py +0 -0
- {ThinkSound β PrismAudio}/models/mmmodules/ext/rotary_embeddings.py +0 -0
- {ThinkSound β PrismAudio}/models/mmmodules/ext/stft_converter.py +0 -0
- {ThinkSound β PrismAudio}/models/mmmodules/ext/stft_converter_mel.py +0 -0
- {ThinkSound β PrismAudio}/models/mmmodules/model/__init__.py +0 -0
- {ThinkSound β PrismAudio}/models/mmmodules/model/embeddings.py +0 -0
{ThinkSound β PrismAudio}/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/configs/model_configs/prismaudio.json
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/configs/model_configs/stable_audio_2_0_vae.json
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/configs/model_configs/thinksound.json
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/configs/multimodal_dataset_demo.json
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/configs/multimodal_dataset_demo_prismaudio.json
RENAMED
|
@@ -3,22 +3,22 @@
|
|
| 3 |
"datasets": [
|
| 4 |
{
|
| 5 |
"id": "vggsound",
|
| 6 |
-
"path": "
|
| 7 |
-
"split_path": "
|
| 8 |
}
|
| 9 |
],
|
| 10 |
"val_datasets": [
|
| 11 |
{
|
| 12 |
"id": "vggsound",
|
| 13 |
-
"path": "test",
|
| 14 |
-
"split_path": "
|
| 15 |
}
|
| 16 |
],
|
| 17 |
"test_datasets": [
|
| 18 |
{
|
| 19 |
"id": "vggsound",
|
| 20 |
-
"path": "test",
|
| 21 |
-
"split_path": "
|
| 22 |
}
|
| 23 |
],
|
| 24 |
"random_crop": false,
|
|
|
|
| 3 |
"datasets": [
|
| 4 |
{
|
| 5 |
"id": "vggsound",
|
| 6 |
+
"path": "data/train",
|
| 7 |
+
"split_path": "split/train.txt"
|
| 8 |
}
|
| 9 |
],
|
| 10 |
"val_datasets": [
|
| 11 |
{
|
| 12 |
"id": "vggsound",
|
| 13 |
+
"path": "data/test",
|
| 14 |
+
"split_path": "split/test.txt"
|
| 15 |
}
|
| 16 |
],
|
| 17 |
"test_datasets": [
|
| 18 |
{
|
| 19 |
"id": "vggsound",
|
| 20 |
+
"path": "data/test",
|
| 21 |
+
"split_path": "split/test.txt"
|
| 22 |
}
|
| 23 |
],
|
| 24 |
"random_crop": false,
|
{ThinkSound β PrismAudio}/data/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/data/datamodule.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/data/dataset.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/data/utils.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/inference/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/inference/generation.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/inference/sampling.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/inference/utils.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/interface/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/interface/aeiou.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/interface/gradio.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/adp.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/autoencoders.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/blocks.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/bottleneck.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/codebook_patterns.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/conditioners.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/diffusion.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/diffusion_prior.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/discriminators.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/dit (1).py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/dit.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/factory.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/lm.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/lm_backbone.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/lm_continuous.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/local_attention.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/meta_queries/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/meta_queries/metaquery.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/meta_queries/model.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/meta_queries/models/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/meta_queries/models/process_audio_info.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/meta_queries/models/qwen25VL.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/meta_queries/models/qwen25omni.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/meta_queries/transformer_encoder.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/mmdit.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/mmmodules/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/mmmodules/ext/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/mmmodules/ext/rotary_embeddings.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/mmmodules/ext/stft_converter.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/mmmodules/ext/stft_converter_mel.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/mmmodules/model/__init__.py
RENAMED
|
File without changes
|
{ThinkSound β PrismAudio}/models/mmmodules/model/embeddings.py
RENAMED
|
File without changes
|