Commit
•
ff1a788
1
Parent(s):
81e7f9e
Update README.md
Browse files
README.md
CHANGED
@@ -23,12 +23,12 @@ This is the **large** version of the AudioLDM model, with twice the number of UN
|
|
23 |
|
24 |
**Table 1:** Summary of the AudioLDM checkpoints.
|
25 |
|
26 |
-
| Checkpoint | Training
|
27 |
-
|
28 |
-
| [audioldm-s-full](https://huggingface.co/cvssp/audioldm) |
|
29 |
-
| [audioldm-s-full-v2](https://huggingface.co/cvssp/audioldm-s-full-v2) |
|
30 |
-
| [audioldm-m-full](https://huggingface.co/cvssp/audioldm-m-full) |
|
31 |
-
| [audioldm-l-full](https://huggingface.co/cvssp/audioldm-l-full) |
|
32 |
|
33 |
|
34 |
## Model Sources
|
|
|
23 |
|
24 |
**Table 1:** Summary of the AudioLDM checkpoints.
|
25 |
|
26 |
+
| Checkpoint | Training Steps | Audio conditioning | CLAP audio dim | UNet dim | Params |
|
27 |
+
|-----------------------------------------------------------------------|----------------|--------------------|----------------|----------|--------|
|
28 |
+
| [audioldm-s-full](https://huggingface.co/cvssp/audioldm) | 1.5M | No | 768 | 128 | 421M |
|
29 |
+
| [audioldm-s-full-v2](https://huggingface.co/cvssp/audioldm-s-full-v2) | > 1.5M | No | 768 | 128 | 421M |
|
30 |
+
| [audioldm-m-full](https://huggingface.co/cvssp/audioldm-m-full) | 1.5M | Yes | 1024 | 192 | 652M |
|
31 |
+
| [audioldm-l-full](https://huggingface.co/cvssp/audioldm-l-full) | 1.5M | No | 768 | 256 | 975M |
|
32 |
|
33 |
|
34 |
## Model Sources
|