Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -30,6 +30,7 @@ MS2KU-VTTS generates immersive, spatially-aware speech by understanding multi-so
|
|
| 30 |
| Pretrain Encoder | `checkpoints/pretrain_encoder/` | Pretrained TTS encoder |
|
| 31 |
| Pretrain Decoder | `checkpoints/pretrain_decoder/` | Pretrained DiT decoder (ControlNet backbone) |
|
| 32 |
| BigVGAN v2 | `checkpoints/bigvgan/` | Retrained vocoder (16 kHz) |
|
|
|
|
| 33 |
|
| 34 |
The following third-party checkpoints are also required. Please download from their official sources:
|
| 35 |
|
|
|
|
| 30 |
| Pretrain Encoder | `checkpoints/pretrain_encoder/` | Pretrained TTS encoder |
|
| 31 |
| Pretrain Decoder | `checkpoints/pretrain_decoder/` | Pretrained DiT decoder (ControlNet backbone) |
|
| 32 |
| BigVGAN v2 | `checkpoints/bigvgan/` | Retrained vocoder (16 kHz) |
|
| 33 |
+
| Spatial environment captions | `data/raw_data/captions/` | Gemini-generated captions for all splits |
|
| 34 |
|
| 35 |
The following third-party checkpoints are also required. Please download from their official sources:
|
| 36 |
|