Xenova HF staff commited on
Commit
2b26158
1 Parent(s): 8ba0d33

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<ctc_blank>": 80,
4
+ "<mask>": 79,
5
+ "<pad>": 1,
6
+ "<s>": 0,
7
+ "<unk>": 3
8
+ }
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/speecht5_tts",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "SpeechT5ForTextToSpeech"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "conv_bias": false,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "decoder_attention_heads": 12,
39
+ "decoder_ffn_dim": 3072,
40
+ "decoder_layerdrop": 0.1,
41
+ "decoder_layers": 6,
42
+ "decoder_start_token_id": 2,
43
+ "encoder_attention_heads": 12,
44
+ "encoder_ffn_dim": 3072,
45
+ "encoder_layerdrop": 0.1,
46
+ "encoder_layers": 12,
47
+ "encoder_max_relative_position": 160,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.0,
52
+ "guided_attention_loss_num_heads": 2,
53
+ "guided_attention_loss_scale": 10.0,
54
+ "guided_attention_loss_sigma": 0.4,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "is_encoder_decoder": true,
60
+ "layer_norm_eps": 1e-05,
61
+ "mask_feature_length": 10,
62
+ "mask_feature_min_masks": 0,
63
+ "mask_feature_prob": 0.0,
64
+ "mask_time_length": 10,
65
+ "mask_time_min_masks": 2,
66
+ "mask_time_prob": 0.05,
67
+ "max_length": 1876,
68
+ "max_speech_positions": 1876,
69
+ "max_text_positions": 600,
70
+ "model_type": "speecht5",
71
+ "num_conv_pos_embedding_groups": 16,
72
+ "num_conv_pos_embeddings": 128,
73
+ "num_feat_extract_layers": 7,
74
+ "num_mel_bins": 80,
75
+ "pad_token_id": 1,
76
+ "positional_dropout": 0.1,
77
+ "reduction_factor": 2,
78
+ "scale_embedding": false,
79
+ "speaker_embedding_dim": 512,
80
+ "speech_decoder_postnet_dropout": 0.5,
81
+ "speech_decoder_postnet_kernel": 5,
82
+ "speech_decoder_postnet_layers": 5,
83
+ "speech_decoder_postnet_units": 256,
84
+ "speech_decoder_prenet_dropout": 0.5,
85
+ "speech_decoder_prenet_layers": 2,
86
+ "speech_decoder_prenet_units": 256,
87
+ "transformers_version": "4.34.0.dev0",
88
+ "use_cache": true,
89
+ "use_guided_attention_loss": true,
90
+ "vocab_size": 81
91
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "max_length": 1876,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.34.0.dev0"
9
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f9a2eaf23c51181f115dfde708c8caf9e22b18fd148b680bcea59da58977fe
3
+ size 238455017
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75879674ca1f08b6ca794bb3965ecc5392b1af329516457ba91794bbeb07b6d4
3
+ size 64901194
onnx/decoder_postnet_and_vocoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26408d9b8b3e83e66a3ef614a5621b84cacdcabd81b3a6a2fa984eb788566e6c
3
+ size 55432026
onnx/decoder_postnet_and_vocoder_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d092ea63bbc7839f7317657b5f531ebb68377ee05ec866ec096dba25911f9feb
3
+ size 18251672
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a676c62303a4d29ea3ba026a698de4877ee0b0be60350c9f283eb4c5369fad08
3
+ size 342803468
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407375255d220d8ddf81e9a06d4100f80f870f8446e77d4f20951d2a4c08a156
3
+ size 88402301
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "SpeechT5FeatureExtractor",
4
+ "feature_size": 1,
5
+ "fmax": 7600,
6
+ "fmin": 80,
7
+ "frame_signal_scale": 1.0,
8
+ "hop_length": 16,
9
+ "mel_floor": 1e-10,
10
+ "num_mel_bins": 80,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "processor_class": "SpeechT5Processor",
14
+ "reduction_factor": 2,
15
+ "return_attention_mask": true,
16
+ "sampling_rate": 16000,
17
+ "win_function": "hann_window",
18
+ "win_length": 64
19
+ }
quantize_config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "encoder_model": {
6
+ "op_types": [
7
+ "Add",
8
+ "Sub",
9
+ "Pow",
10
+ "Reshape",
11
+ "Cast",
12
+ "Less",
13
+ "Transpose",
14
+ "Where",
15
+ "ConstantOfShape",
16
+ "Sqrt",
17
+ "Mul",
18
+ "Gather",
19
+ "Div",
20
+ "Expand",
21
+ "ReduceMean",
22
+ "Concat",
23
+ "Not",
24
+ "Constant",
25
+ "Shape",
26
+ "Erf",
27
+ "Unsqueeze",
28
+ "Softmax",
29
+ "Range",
30
+ "Slice",
31
+ "Equal",
32
+ "MatMul"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "decoder_model": {
37
+ "op_types": [
38
+ "Add",
39
+ "Sub",
40
+ "Pow",
41
+ "Reshape",
42
+ "Cast",
43
+ "Transpose",
44
+ "Where",
45
+ "ConstantOfShape",
46
+ "Sqrt",
47
+ "Sigmoid",
48
+ "Relu",
49
+ "Mul",
50
+ "Gather",
51
+ "Div",
52
+ "ReduceSum",
53
+ "Expand",
54
+ "ReduceMean",
55
+ "Concat",
56
+ "Clip",
57
+ "Abs",
58
+ "Constant",
59
+ "Dropout",
60
+ "Shape",
61
+ "Erf",
62
+ "Unsqueeze",
63
+ "Softmax",
64
+ "Slice",
65
+ "Equal",
66
+ "MatMul"
67
+ ],
68
+ "weight_type": "QInt8"
69
+ },
70
+ "decoder_postnet_and_vocoder": {
71
+ "op_types": [
72
+ "Conv",
73
+ "Add",
74
+ "Tanh",
75
+ "Unsqueeze",
76
+ "Squeeze",
77
+ "Sub",
78
+ "Reshape",
79
+ "Transpose",
80
+ "Div",
81
+ "Constant",
82
+ "ConvTranspose",
83
+ "LeakyRelu"
84
+ ],
85
+ "weight_type": "QUInt8"
86
+ }
87
+ }
88
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
spm_char.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
3
+ size 238473
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "79": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "80": {
44
+ "content": "<ctc_blank>",
45
+ "lstrip": true,
46
+ "normalized": true,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ }
51
+ },
52
+ "additional_special_tokens": [],
53
+ "bos_token": "<s>",
54
+ "clean_up_tokenization_spaces": true,
55
+ "eos_token": "</s>",
56
+ "model_max_length": 600,
57
+ "normalize": false,
58
+ "pad_token": "<pad>",
59
+ "processor_class": "SpeechT5Processor",
60
+ "sp_model_kwargs": {},
61
+ "tokenizer_class": "SpeechT5Tokenizer",
62
+ "tokenizer_file": null,
63
+ "trust_remote_code": false,
64
+ "unk_token": "<unk>"
65
+ }