GeWu-Lab commited on
Commit
3186ced
·
verified ·
1 Parent(s): fc68fed

Link one shared source audio and preparation guide for training workflows

Browse files
Files changed (2) hide show
  1. README.md +2 -2
  2. manifest.json +2 -2
README.md CHANGED
@@ -104,11 +104,11 @@ Input files are downmixed to mono, resampled to 16 kHz, and truncated or right-p
104
 
105
  ## Fine-tuning
106
 
107
- **Pretraining and standard FM fine-tuning:** use the [original audio datasets used in our paper](https://github.com/GeWu-Lab/SteerSound/blob/main/pretrain_and_standard_FM_finetune/dataset/SOURCES.md) or your own audio–caption data. Obtain raw audio from its original datasets and follow the [format and processing guide](https://github.com/GeWu-Lab/SteerSound/blob/main/pretrain_and_standard_FM_finetune/dataset/README.md). 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.
108
 
109
  **STEER post-training:** start from the released [SteerSound checkpoint](https://huggingface.co/GeWu-Lab/SteerSound) and choose one of these settings:
110
 
111
- 1. **Complex audio editing data / your own data:** prepare the original audio datasets used in our paper, or your own audio–caption data, using the same guide. Apply [Emphasis](https://github.com/GeWu-Lab/SteerSound/tree/main/STEER_post_training/emphasis/complex) or [Recovery](https://github.com/GeWu-Lab/SteerSound/tree/main/STEER_post_training/recovery/complex) with online editing-example construction; validate and evaluate on `complex_val` / `complex_test`.
112
  2. **Selective audio editing data:** download the released `selective_train`, `selective_val`, and `selective_test` from the [🤗 dataset](https://huggingface.co/datasets/GeWu-Lab/SteerSound). Follow [Emphasis / Selective](https://github.com/GeWu-Lab/SteerSound/tree/main/STEER_post_training/emphasis/selective) or [Recovery / Selective](https://github.com/GeWu-Lab/SteerSound/tree/main/STEER_post_training/recovery/selective) to post-train on the supplied editing pairs and evaluate on the corresponding splits.
113
 
114
  ## Model files
 
104
 
105
  ## Fine-tuning
106
 
107
+ **Pretraining and standard FM fine-tuning:** 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.
108
 
109
  **STEER post-training:** start from the released [SteerSound checkpoint](https://huggingface.co/GeWu-Lab/SteerSound) and choose one of these settings:
110
 
111
+ 1. **Complex audio editing data:** prepare the paper's source audio or your own audio–caption data with the same [Source audio and preparation](https://github.com/GeWu-Lab/SteerSound/blob/main/pretrain_and_standard_FM_finetune/dataset/README.md) guide. Apply [Emphasis](https://github.com/GeWu-Lab/SteerSound/tree/main/STEER_post_training/emphasis/complex) or [Recovery](https://github.com/GeWu-Lab/SteerSound/tree/main/STEER_post_training/recovery/complex) with online editing-example construction; validate and evaluate on `complex_val` / `complex_test`.
112
  2. **Selective audio editing data:** download the released `selective_train`, `selective_val`, and `selective_test` from the [🤗 dataset](https://huggingface.co/datasets/GeWu-Lab/SteerSound). Follow [Emphasis / Selective](https://github.com/GeWu-Lab/SteerSound/tree/main/STEER_post_training/emphasis/selective) or [Recovery / Selective](https://github.com/GeWu-Lab/SteerSound/tree/main/STEER_post_training/recovery/selective) to post-train on the supplied editing pairs and evaluate on the corresponding splits.
113
 
114
  ## Model files
manifest.json CHANGED
@@ -6,8 +6,8 @@
6
  "sha256": "1851bd54305514445591afe73dec20f7142d93892ae24d0fc62dc2855f4d0009"
7
  },
8
  "README.md": {
9
- "bytes": 6859,
10
- "sha256": "d26ac0841fc42de54198d3767bd5e4263fe97a99b2e1520938b5634fd4a49dc3"
11
  },
12
  "dit/model.safetensors": {
13
  "bytes": 1346719328,
 
6
  "sha256": "1851bd54305514445591afe73dec20f7142d93892ae24d0fc62dc2855f4d0009"
7
  },
8
  "README.md": {
9
+ "bytes": 6877,
10
+ "sha256": "6e03643597c2856e590579f62fa5e9c71bd794a5ce50e34ad5854a9576014b66"
11
  },
12
  "dit/model.safetensors": {
13
  "bytes": 1346719328,