Hugging Face's logo

Cseti
/
VibeVoice_7B_hun_v2

Text-to-Speech
VibeVoice
Safetensors
Hungarian
tts
lora
sft
full-finetune
Model card Files
xet
Community
Cseti commited on
Commit
6b08e8c
·
verified ·
1 Parent(s): ab96199

Upload 10 files

Browse files
Files changed (10) hide show
  1. config.json +120 -0
  2. model-00001-of-00008.safetensors +3 -0
  3. model-00002-of-00008.safetensors +3 -0
  4. model-00003-of-00008.safetensors +3 -0
  5. model-00004-of-00008.safetensors +3 -0
  6. model-00005-of-00008.safetensors +3 -0
  7. model-00006-of-00008.safetensors +3 -0
  8. model-00007-of-00008.safetensors +3 -0
  9. model-00008-of-00008.safetensors +3 -0
  10. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "acostic_vae_dim": 64,
3
+ "acoustic_tokenizer_config": {
4
+ "causal": true,
5
+ "channels": 1,
6
+ "conv_bias": true,
7
+ "conv_norm": "none",
8
+ "corpus_normalize": 0.0,
9
+ "decoder_depths": null,
10
+ "decoder_n_filters": 32,
11
+ "decoder_ratios": [
12
+ 8,
13
+ 5,
14
+ 5,
15
+ 4,
16
+ 2,
17
+ 2
18
+ ],
19
+ "disable_last_norm": true,
20
+ "encoder_depths": "3-3-3-3-3-3-8",
21
+ "encoder_n_filters": 32,
22
+ "encoder_ratios": [
23
+ 8,
24
+ 5,
25
+ 5,
26
+ 4,
27
+ 2,
28
+ 2
29
+ ],
30
+ "fix_std": 0.5,
31
+ "layer_scale_init_value": 1e-06,
32
+ "layernorm": "RMSNorm",
33
+ "layernorm_elementwise_affine": true,
34
+ "layernorm_eps": 1e-05,
35
+ "mixer_layer": "depthwise_conv",
36
+ "model_type": "vibevoice_acoustic_tokenizer",
37
+ "pad_mode": "constant",
38
+ "std_dist_type": "gaussian",
39
+ "torch_dtype": "float32",
40
+ "vae_dim": 64,
41
+ "weight_init_value": 0.01
42
+ },
43
+ "acoustic_vae_dim": 64,
44
+ "architectures": [
45
+ "VibeVoiceForConditionalGeneration"
46
+ ],
47
+ "decoder_config": {
48
+ "attention_dropout": 0.0,
49
+ "hidden_act": "silu",
50
+ "hidden_size": 3584,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 18944,
53
+ "max_position_embeddings": 32768,
54
+ "max_window_layers": 28,
55
+ "model_type": "qwen2",
56
+ "num_attention_heads": 28,
57
+ "num_hidden_layers": 28,
58
+ "num_key_value_heads": 4,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 1000000.0,
62
+ "sliding_window": null,
63
+ "torch_dtype": "float32",
64
+ "use_cache": true,
65
+ "use_mrope": false,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 152064
68
+ },
69
+ "diffusion_head_config": {
70
+ "ddpm_batch_mul": 4,
71
+ "ddpm_beta_schedule": "cosine",
72
+ "ddpm_num_inference_steps": 20,
73
+ "ddpm_num_steps": 1000,
74
+ "diffusion_type": "ddpm",
75
+ "head_ffn_ratio": 3.0,
76
+ "head_layers": 4,
77
+ "hidden_size": 3584,
78
+ "latent_size": 64,
79
+ "model_type": "vibevoice_diffusion_head",
80
+ "prediction_type": "v_prediction",
81
+ "rms_norm_eps": 1e-05,
82
+ "speech_vae_dim": 64,
83
+ "torch_dtype": "float32"
84
+ },
85
+ "model_type": "vibevoice",
86
+ "semantic_tokenizer_config": {
87
+ "causal": true,
88
+ "channels": 1,
89
+ "conv_bias": true,
90
+ "conv_norm": "none",
91
+ "corpus_normalize": 0.0,
92
+ "disable_last_norm": true,
93
+ "encoder_depths": "3-3-3-3-3-3-8",
94
+ "encoder_n_filters": 32,
95
+ "encoder_ratios": [
96
+ 8,
97
+ 5,
98
+ 5,
99
+ 4,
100
+ 2,
101
+ 2
102
+ ],
103
+ "fix_std": 0,
104
+ "layer_scale_init_value": 1e-06,
105
+ "layernorm": "RMSNorm",
106
+ "layernorm_elementwise_affine": true,
107
+ "layernorm_eps": 1e-05,
108
+ "mixer_layer": "depthwise_conv",
109
+ "model_type": "vibevoice_semantic_tokenizer",
110
+ "pad_mode": "constant",
111
+ "std_dist_type": "none",
112
+ "torch_dtype": "float32",
113
+ "vae_dim": 128,
114
+ "weight_init_value": 0.01
115
+ },
116
+ "semantic_vae_dim": 128,
117
+ "tie_word_embeddings": false,
118
+ "torch_dtype": "float32",
119
+ "transformers_version": "4.51.3"
120
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7086a2b47543884277afd3bd923ad3dce9dd26a8717ff5b11a62e18aae7b84d7
3
+ size 4976687968
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8fb40ef699d78f8b90c84a9869d7a4ae5795d38bc34644f07fc7726dacb4a91
3
+ size 4778623360
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d50beb2b59a792b102e1232c1b33335ff9e793e8fb8fc3afea26de4cb9a450
3
+ size 4932744880
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58c88b9649a5aeb2b601ff70ce7991c591b1c66f5fedc1338690c568072387c
3
+ size 4932744904
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4253246628c299922e64d1b0d6ffb294f33c96396ec1bc77910a4349b77a7c4
3
+ size 4998853328
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7284b3d48bdb5901dba58ffe67d0d0894368865d63f31f1deca1b243d117582f
3
+ size 4966898568
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da7e52ba72650d46ed6d8fed5cf2a6666972c7a9b9b6a7885f2ac6367267586
3
+ size 4886781532
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d4f401fefefde8be8bb67d101d7af85384a4f460bd7eb3327d4f4cc597821a
3
+ size 2900245504
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff