Hugging Face's logo

Cseti
/
VibeVoice_7B_Diffusion-head-LoRA_Hungarian-CV17

Text-to-Speech
Safetensors
Hungarian
tts
lora
vibevice
Model card Files
xet
Community
2
Cseti commited on
Commit
476ae37
·
verified ·
1 Parent(s): d17f1a3

Upload LoRA files

Browse files
Files changed (6) hide show
  1. diffusion_head1200/diffusion_head/config.json +20 -0
  2. diffusion_head1200/diffusion_head/model.safetensors +3 -0
  3. diffusion_head600/diffusion_head/config.json +20 -0
  4. diffusion_head600/diffusion_head/model.safetensors +3 -0
  5. diffusion_head900/diffusion_head/config.json +20 -0
  6. diffusion_head900/diffusion_head/model.safetensors +3 -0
diffusion_head1200/diffusion_head/config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VibeVoiceDiffusionHead"
4
+ ],
5
+ "ddpm_batch_mul": 4,
6
+ "ddpm_beta_schedule": "cosine",
7
+ "ddpm_num_inference_steps": 20,
8
+ "ddpm_num_steps": 1000,
9
+ "diffusion_type": "ddpm",
10
+ "head_ffn_ratio": 3.0,
11
+ "head_layers": 4,
12
+ "hidden_size": 3584,
13
+ "latent_size": 64,
14
+ "model_type": "vibevoice_diffusion_head",
15
+ "prediction_type": "v_prediction",
16
+ "rms_norm_eps": 1e-05,
17
+ "speech_vae_dim": 64,
18
+ "torch_dtype": "bfloat16",
19
+ "transformers_version": "4.51.3"
20
+ }
diffusion_head1200/diffusion_head/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14240b23785864b4fdfdc83f3e9031ef1469eb20dcfc6dd875a98cd8ac65f3ec
3
+ size 1338669752
diffusion_head600/diffusion_head/config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VibeVoiceDiffusionHead"
4
+ ],
5
+ "ddpm_batch_mul": 4,
6
+ "ddpm_beta_schedule": "cosine",
7
+ "ddpm_num_inference_steps": 20,
8
+ "ddpm_num_steps": 1000,
9
+ "diffusion_type": "ddpm",
10
+ "head_ffn_ratio": 3.0,
11
+ "head_layers": 4,
12
+ "hidden_size": 3584,
13
+ "latent_size": 64,
14
+ "model_type": "vibevoice_diffusion_head",
15
+ "prediction_type": "v_prediction",
16
+ "rms_norm_eps": 1e-05,
17
+ "speech_vae_dim": 64,
18
+ "torch_dtype": "bfloat16",
19
+ "transformers_version": "4.51.3"
20
+ }
diffusion_head600/diffusion_head/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7fe144ce07aeaf95b908642837d7d1e4f00f92bfcd8f371130a2dffbc90aee3
3
+ size 1338669752
diffusion_head900/diffusion_head/config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VibeVoiceDiffusionHead"
4
+ ],
5
+ "ddpm_batch_mul": 4,
6
+ "ddpm_beta_schedule": "cosine",
7
+ "ddpm_num_inference_steps": 20,
8
+ "ddpm_num_steps": 1000,
9
+ "diffusion_type": "ddpm",
10
+ "head_ffn_ratio": 3.0,
11
+ "head_layers": 4,
12
+ "hidden_size": 3584,
13
+ "latent_size": 64,
14
+ "model_type": "vibevoice_diffusion_head",
15
+ "prediction_type": "v_prediction",
16
+ "rms_norm_eps": 1e-05,
17
+ "speech_vae_dim": 64,
18
+ "torch_dtype": "bfloat16",
19
+ "transformers_version": "4.51.3"
20
+ }
diffusion_head900/diffusion_head/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:224bbf445786e51ad464b84d8af52db9b4d08967bc90628a1d24bd212a3f73af
3
+ size 1338669752