Xenova HF staff commited on
Commit
ac44bfe
1 Parent(s): 8dc66dc

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 34
3
+ }
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mms-tts-ron",
3
+ "activation_dropout": 0.1,
4
+ "architectures": [
5
+ "VitsModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "depth_separable_channels": 2,
9
+ "depth_separable_num_layers": 3,
10
+ "duration_predictor_dropout": 0.5,
11
+ "duration_predictor_filter_channels": 256,
12
+ "duration_predictor_flow_bins": 10,
13
+ "duration_predictor_kernel_size": 3,
14
+ "duration_predictor_num_flows": 4,
15
+ "duration_predictor_tail_bound": 5.0,
16
+ "ffn_dim": 768,
17
+ "ffn_kernel_size": 3,
18
+ "flow_size": 192,
19
+ "hidden_act": "relu",
20
+ "hidden_dropout": 0.1,
21
+ "hidden_size": 192,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_eps": 1e-05,
24
+ "layerdrop": 0.1,
25
+ "leaky_relu_slope": 0.1,
26
+ "model_type": "vits",
27
+ "noise_scale": 0.667,
28
+ "noise_scale_duration": 0.8,
29
+ "num_attention_heads": 2,
30
+ "num_hidden_layers": 6,
31
+ "num_speakers": 1,
32
+ "posterior_encoder_num_wavenet_layers": 16,
33
+ "prior_encoder_num_flows": 4,
34
+ "prior_encoder_num_wavenet_layers": 4,
35
+ "resblock_dilation_sizes": [
36
+ [
37
+ 1,
38
+ 3,
39
+ 5
40
+ ],
41
+ [
42
+ 1,
43
+ 3,
44
+ 5
45
+ ],
46
+ [
47
+ 1,
48
+ 3,
49
+ 5
50
+ ]
51
+ ],
52
+ "resblock_kernel_sizes": [
53
+ 3,
54
+ 7,
55
+ 11
56
+ ],
57
+ "sampling_rate": 16000,
58
+ "speaker_embedding_size": 0,
59
+ "speaking_rate": 1.0,
60
+ "spectrogram_bins": 513,
61
+ "transformers_version": "4.37.0.dev0",
62
+ "upsample_initial_channel": 512,
63
+ "upsample_kernel_sizes": [
64
+ 16,
65
+ 16,
66
+ 4,
67
+ 4
68
+ ],
69
+ "upsample_rates": [
70
+ 8,
71
+ 8,
72
+ 2,
73
+ 2
74
+ ],
75
+ "use_bias": true,
76
+ "use_stochastic_duration_prediction": true,
77
+ "vocab_size": 34,
78
+ "wavenet_dilation_rate": 1,
79
+ "wavenet_dropout": 0.0,
80
+ "wavenet_kernel_size": 5,
81
+ "window_size": 4
82
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53be0a275b045f9b3b9117aeb2edfda0126113e52bd7db48fff181a8341b424e
3
+ size 114255734
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c3f3c79e9db38098b8e5c0f02c2e4eb87b71e307a07ae8bf63f7a0f1beaa5c
3
+ size 38360875
quantize_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Pow",
8
+ "Reshape",
9
+ "Split",
10
+ "Neg",
11
+ "Cast",
12
+ "Pad",
13
+ "Softmax",
14
+ "Clip",
15
+ "Less",
16
+ "Sqrt",
17
+ "Greater",
18
+ "Softplus",
19
+ "RandomNormalLike",
20
+ "Slice",
21
+ "Tanh",
22
+ "CumSum",
23
+ "Transpose",
24
+ "Div",
25
+ "Unsqueeze",
26
+ "ReduceSum",
27
+ "Constant",
28
+ "ReduceMean",
29
+ "GatherND",
30
+ "GatherElements",
31
+ "ScatterND",
32
+ "ReduceMax",
33
+ "NonZero",
34
+ "Sub",
35
+ "Sigmoid",
36
+ "ConvTranspose",
37
+ "Erf",
38
+ "Concat",
39
+ "Conv",
40
+ "Squeeze",
41
+ "LeakyRelu",
42
+ "Mul",
43
+ "Not",
44
+ "MatMul",
45
+ "Range",
46
+ "Shape",
47
+ "Expand",
48
+ "Where",
49
+ "Exp",
50
+ "Ceil",
51
+ "ConstantOfShape",
52
+ "Add",
53
+ "Equal",
54
+ "Gather",
55
+ "Relu",
56
+ "And"
57
+ ],
58
+ "weight_type": "QUInt8"
59
+ }
60
+ }
61
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "c",
3
+ "unk_token": "<unk>"
4
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "c",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "34": {
13
+ "content": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "clean_up_tokenization_spaces": true,
22
+ "is_uroman": false,
23
+ "language": "ron",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": true,
26
+ "pad_token": "c",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>"
30
+ }
vocab.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 28,
3
+ "'": 23,
4
+ "-": 20,
5
+ "1": 17,
6
+ "_": 5,
7
+ "a": 16,
8
+ "b": 3,
9
+ "c": 0,
10
+ "d": 33,
11
+ "e": 25,
12
+ "f": 14,
13
+ "g": 4,
14
+ "h": 21,
15
+ "i": 10,
16
+ "j": 26,
17
+ "l": 12,
18
+ "m": 8,
19
+ "n": 6,
20
+ "o": 31,
21
+ "p": 19,
22
+ "q": 1,
23
+ "r": 29,
24
+ "s": 22,
25
+ "t": 11,
26
+ "u": 2,
27
+ "v": 30,
28
+ "x": 24,
29
+ "z": 9,
30
+ "â": 27,
31
+ "î": 18,
32
+ "ă": 13,
33
+ "ţ": 32,
34
+ "ș": 15,
35
+ "–": 7
36
+ }