Simplify model size and total inference memory requirements
Browse files- README.md +9 -11
- manifest.json +2 -2
README.md
CHANGED
|
@@ -88,19 +88,17 @@ For pitch and volume, use `Increase` or `Reduce` with an explicit magnitude. Vol
|
|
| 88 |
|
| 89 |
Input files are downmixed to mono, resampled to 16 kHz, and truncated or right-padded to 10 seconds. Output is a 10-second mono waveform at 16 kHz. The default runtime uses BF16, PyTorch SDPA and 50 Euler steps, with guidance scale 8.5 for Addition and 3.5 for the other tasks. Use `--seed` with the CLI or `seed=...` with the Python API for repeatable sampling.
|
| 90 |
|
| 91 |
-
##
|
| 92 |
|
| 93 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
|
| 95 |
-
|
| 96 |
-
|---|---:|---:|
|
| 97 |
-
| DiT editor | 673,349,696 | 1.254 |
|
| 98 |
-
| Audio VAE | 509,336,866 | 0.949 |
|
| 99 |
-
| T5 encoder | 109,628,544 | 0.204 |
|
| 100 |
-
| HiFi-GAN vocoder | 55,264,897 | 0.103 |
|
| 101 |
-
| Total | 1,347,580,003 | 2.510 |
|
| 102 |
-
|
| 103 |
-
Estimated total inference memory is **4–8 GiB VRAM**; **8 GiB or more is recommended**. This is an estimate, not a CUDA measurement. The total includes weight storage, activations, workspaces and runtime overhead, and can vary with hardware and library versions. Inference uses no CPU offload. See [MEMORY.md](https://github.com/GeWu-Lab/SteerSound/blob/main/MEMORY.md) for details.
|
| 104 |
|
| 105 |
## Files and data
|
| 106 |
|
|
|
|
| 88 |
|
| 89 |
Input files are downmixed to mono, resampled to 16 kHz, and truncated or right-padded to 10 seconds. Output is a 10-second mono waveform at 16 kHz. The default runtime uses BF16, PyTorch SDPA and 50 Euler steps, with guidance scale 8.5 for Addition and 3.5 for the other tasks. Use `--seed` with the CLI or `seed=...` with the Python API for repeatable sampling.
|
| 90 |
|
| 91 |
+
## Model size and GPU memory
|
| 92 |
|
| 93 |
+
| Component | Parameters |
|
| 94 |
+
|---|---:|
|
| 95 |
+
| DiT editor | 673,349,696 |
|
| 96 |
+
| Audio VAE | 509,336,866 |
|
| 97 |
+
| T5 encoder | 109,628,544 |
|
| 98 |
+
| HiFi-GAN vocoder | 55,264,897 |
|
| 99 |
+
| Total | **1,347,580,003** |
|
| 100 |
|
| 101 |
+
**GPU memory for inference: approximately 8 GB** (BF16, batch size 1, 10-second audio).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
|
| 103 |
## Files and data
|
| 104 |
|
manifest.json
CHANGED
|
@@ -6,8 +6,8 @@
|
|
| 6 |
"sha256": "1851bd54305514445591afe73dec20f7142d93892ae24d0fc62dc2855f4d0009"
|
| 7 |
},
|
| 8 |
"README.md": {
|
| 9 |
-
"bytes":
|
| 10 |
-
"sha256": "
|
| 11 |
},
|
| 12 |
"dit/model.safetensors": {
|
| 13 |
"bytes": 1346719328,
|
|
|
|
| 6 |
"sha256": "1851bd54305514445591afe73dec20f7142d93892ae24d0fc62dc2855f4d0009"
|
| 7 |
},
|
| 8 |
"README.md": {
|
| 9 |
+
"bytes": 4848,
|
| 10 |
+
"sha256": "9331b1f1e0c132b07bbee95b3865924da68dcd38fa805617a4816a9d9635302d"
|
| 11 |
},
|
| 12 |
"dit/model.safetensors": {
|
| 13 |
"bytes": 1346719328,
|