Clarify pretraining and fine-tuning with standard FM
Browse files- README.md +1 -1
- manifest.json +2 -2
README.md
CHANGED
|
@@ -102,7 +102,7 @@ Input files are downmixed to mono, resampled to 16 kHz, and truncated or right-p
|
|
| 102 |
|
| 103 |
## Fine-tuning
|
| 104 |
|
| 105 |
-
**Pretraining and
|
| 106 |
|
| 107 |
**STEER post-training:** start from the released [SteerSound checkpoint](https://huggingface.co/GeWu-Lab/SteerSound) and choose one of these settings:
|
| 108 |
|
|
|
|
| 102 |
|
| 103 |
## Fine-tuning
|
| 104 |
|
| 105 |
+
**Pretraining and fine-tuning with standard FM:** follow [Source audio and preparation](https://github.com/GeWu-Lab/SteerSound/blob/main/pretrain_and_standard_FM_finetune/dataset/README.md) to prepare the paper's source audio or your own audio–caption data. This shared guide covers source dataset links, formats, processing steps, and expected outputs. Editing examples are constructed online. Use the [standard training guide](https://github.com/GeWu-Lab/SteerSound/tree/main/pretrain_and_standard_FM_finetune) to pretrain or fine-tune, then evaluate on Complex val/test.
|
| 106 |
|
| 107 |
**STEER post-training:** start from the released [SteerSound checkpoint](https://huggingface.co/GeWu-Lab/SteerSound) and choose one of these settings:
|
| 108 |
|
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": 6718,
|
| 10 |
+
"sha256": "ff2a34780d5df653fd3c54bcbc08dfc2eacba053aa44c3d155f81ff19c448a2b"
|
| 11 |
},
|
| 12 |
"dit/model.safetensors": {
|
| 13 |
"bytes": 1346719328,
|