Hugging Face's logo

ymgong3616
/
speecht5_finetuned_rick_leee_emo

TensorBoard
Safetensors
speecht5
Model card Files Metrics Community
ymgong3616 commited on
Commit
8cd74c0
·
verified ·
1 Parent(s): 0909b64

Training in progress, step 1000

Browse files
Files changed (19) hide show
  1. added_tokens.json +8 -0
  2. config.json +92 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +19 -0
  5. runs/Feb07_22-32-03_b4c8d1a80d8d/events.out.tfevents.1738967526.b4c8d1a80d8d.2591.0 +3 -0
  6. runs/Feb07_22-33-28_b4c8d1a80d8d/events.out.tfevents.1738967610.b4c8d1a80d8d.2591.1 +3 -0
  7. runs/Feb07_22-33-50_b4c8d1a80d8d/events.out.tfevents.1738967631.b4c8d1a80d8d.2591.2 +3 -0
  8. runs/Feb07_22-34-51_b4c8d1a80d8d/events.out.tfevents.1738967693.b4c8d1a80d8d.2591.3 +3 -0
  9. runs/Feb07_22-35-38_b4c8d1a80d8d/events.out.tfevents.1738967739.b4c8d1a80d8d.2591.4 +3 -0
  10. runs/Feb07_22-38-04_b4c8d1a80d8d/events.out.tfevents.1738967886.b4c8d1a80d8d.2591.5 +3 -0
  11. runs/Feb07_22-43-49_b4c8d1a80d8d/events.out.tfevents.1738968230.b4c8d1a80d8d.2591.6 +3 -0
  12. runs/Feb07_22-53-48_b4c8d1a80d8d/events.out.tfevents.1738968841.b4c8d1a80d8d.2591.7 +3 -0
  13. runs/Feb07_22-55-30_b4c8d1a80d8d/events.out.tfevents.1738968932.b4c8d1a80d8d.2591.8 +3 -0
  14. runs/Feb07_22-58-26_b4c8d1a80d8d/events.out.tfevents.1738969110.b4c8d1a80d8d.2591.9 +3 -0
  15. runs/Feb07_23-10-27_b4c8d1a80d8d/events.out.tfevents.1738969831.b4c8d1a80d8d.2591.10 +3 -0
  16. special_tokens_map.json +43 -0
  17. spm_char.model +3 -0
  18. tokenizer_config.json +102 -0
  19. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<angry>": 83,
3
+ "<ctc_blank>": 80,
4
+ "<happy>": 81,
5
+ "<mask>": 79,
6
+ "<neutral>": 84,
7
+ "<sad>": 82
8
+ }
config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
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
+ "torch_dtype": "float32",
88
+ "transformers_version": "4.48.2",
89
+ "use_cache": false,
90
+ "use_guided_attention_loss": true,
91
+ "vocab_size": 85
92
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ce68aaf944de3930502dcbae95818b16d549ce39e8d96ab116e26a5861ff17
3
+ size 577801608
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
+ }
runs/Feb07_22-32-03_b4c8d1a80d8d/events.out.tfevents.1738967526.b4c8d1a80d8d.2591.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d28d0c4c0616a7b7c8bb3b0fdb10a80082cb5c482dafea881da85537c723ca
3
+ size 6721
runs/Feb07_22-33-28_b4c8d1a80d8d/events.out.tfevents.1738967610.b4c8d1a80d8d.2591.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed97e77c7915da081ce11d571b7481ed05f7c8c7c13cda786118aba6b90b0b5
3
+ size 6721
runs/Feb07_22-33-50_b4c8d1a80d8d/events.out.tfevents.1738967631.b4c8d1a80d8d.2591.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a0f39f8cab187d470790d1d36fc99405cf3bd94e4509675e0a13f579e35fb1
3
+ size 6721
runs/Feb07_22-34-51_b4c8d1a80d8d/events.out.tfevents.1738967693.b4c8d1a80d8d.2591.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e101f0c8c694894fbf759930010b74b0756f8149e3dd7967c28f2ad72ea48eb2
3
+ size 6721
runs/Feb07_22-35-38_b4c8d1a80d8d/events.out.tfevents.1738967739.b4c8d1a80d8d.2591.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c832a1f8a3a887148bbd42c54f48a3c81db3470d65d99879672ba0efeb2cef28
3
+ size 6721
runs/Feb07_22-38-04_b4c8d1a80d8d/events.out.tfevents.1738967886.b4c8d1a80d8d.2591.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804843b80e37d60ffef1fd6a56b8ad0e6d374967cf7666bafdcc720c88b4868c
3
+ size 6722
runs/Feb07_22-43-49_b4c8d1a80d8d/events.out.tfevents.1738968230.b4c8d1a80d8d.2591.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b519a89fb9635697798a85f95eccb9e5d1419a15aa6533acb39e4a096b6d866e
3
+ size 6722
runs/Feb07_22-53-48_b4c8d1a80d8d/events.out.tfevents.1738968841.b4c8d1a80d8d.2591.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58340f3721a0290aa8222d4f5a56e6b78da663e400ebf2c955a7f4190604197f
3
+ size 6721
runs/Feb07_22-55-30_b4c8d1a80d8d/events.out.tfevents.1738968932.b4c8d1a80d8d.2591.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00806acf55163a709471930ddd75f6352760a9dcf128105111cb91c6390d128
3
+ size 13354
runs/Feb07_22-58-26_b4c8d1a80d8d/events.out.tfevents.1738969110.b4c8d1a80d8d.2591.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a61d0b3dfbb9af2ee137053c9e6ab8ec8c69fc559808e765e714b6df2e28d9c
3
+ size 6721
runs/Feb07_23-10-27_b4c8d1a80d8d/events.out.tfevents.1738969831.b4c8d1a80d8d.2591.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d4b016c4ca25c48dd557caa7cbc637e41c179d7bb177d8ae0f406f3178d638
3
+ size 15412
special_tokens_map.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<happy>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<sad>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<angry>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<neutral>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ ],
32
+ "bos_token": "<s>",
33
+ "eos_token": "</s>",
34
+ "mask_token": {
35
+ "content": "<mask>",
36
+ "lstrip": true,
37
+ "normalized": true,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "pad_token": "<pad>",
42
+ "unk_token": "<unk>"
43
+ }
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 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "80": {
44
+ "content": "<ctc_blank>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "81": {
52
+ "content": "<happy>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "82": {
60
+ "content": "<sad>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "83": {
68
+ "content": "<angry>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "84": {
76
+ "content": "<neutral>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ }
83
+ },
84
+ "additional_special_tokens": [
85
+ "<happy>",
86
+ "<sad>",
87
+ "<angry>",
88
+ "<neutral>"
89
+ ],
90
+ "bos_token": "<s>",
91
+ "clean_up_tokenization_spaces": false,
92
+ "eos_token": "</s>",
93
+ "extra_special_tokens": {},
94
+ "mask_token": "<mask>",
95
+ "model_max_length": 600,
96
+ "normalize": false,
97
+ "pad_token": "<pad>",
98
+ "processor_class": "SpeechT5Processor",
99
+ "sp_model_kwargs": {},
100
+ "tokenizer_class": "SpeechT5Tokenizer",
101
+ "unk_token": "<unk>"
102
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77281278920f8329b8b5403b252ca3a7ef35b20cbc933d9a1d0a95235fc8d3d
3
+ size 5496