duwuonline
commited on
Commit
•
d4d67a9
1
Parent(s):
155c929
Training in progress, step 10
Browse files
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.1,
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
@@ -40,87 +40,43 @@
|
|
40 |
"decoder_layerdrop": 0.1,
|
41 |
"decoder_layers": 6,
|
42 |
"decoder_start_token_id": 2,
|
43 |
-
"
|
44 |
-
"depth_separable_num_layers": 3,
|
45 |
-
"duration_predictor_dropout": 0.5,
|
46 |
-
"duration_predictor_filter_channels": 256,
|
47 |
-
"duration_predictor_flow_bins": 10,
|
48 |
-
"duration_predictor_kernel_size": 3,
|
49 |
-
"duration_predictor_num_flows": 4,
|
50 |
-
"duration_predictor_tail_bound": 5.0,
|
51 |
-
"encoder_attention_heads": 2,
|
52 |
"encoder_ffn_dim": 3072,
|
53 |
"encoder_layerdrop": 0.1,
|
54 |
-
"encoder_layers":
|
55 |
"encoder_max_relative_position": 160,
|
56 |
"eos_token_id": 2,
|
57 |
"feat_extract_activation": "gelu",
|
58 |
"feat_extract_norm": "group",
|
59 |
"feat_proj_dropout": 0.0,
|
60 |
-
"ffn_dim": 768,
|
61 |
-
"ffn_kernel_size": 3,
|
62 |
-
"flow_size": 192,
|
63 |
"guided_attention_loss_num_heads": 2,
|
64 |
"guided_attention_loss_scale": 10.0,
|
65 |
"guided_attention_loss_sigma": 0.4,
|
66 |
-
"hidden_act": "
|
67 |
"hidden_dropout": 0.1,
|
68 |
-
"hidden_size":
|
69 |
"initializer_range": 0.02,
|
70 |
"is_encoder_decoder": true,
|
71 |
"layer_norm_eps": 1e-05,
|
72 |
-
"layerdrop": 0.1,
|
73 |
-
"leaky_relu_slope": 0.1,
|
74 |
"mask_feature_length": 10,
|
75 |
"mask_feature_min_masks": 0,
|
76 |
"mask_feature_prob": 0.0,
|
77 |
"mask_time_length": 10,
|
78 |
"mask_time_min_masks": 2,
|
79 |
"mask_time_prob": 0.05,
|
80 |
-
"
|
81 |
-
"
|
|
|
82 |
"model_type": "speecht5",
|
83 |
-
"noise_scale": 0.667,
|
84 |
-
"noise_scale_duration": 0.8,
|
85 |
"num_conv_pos_embedding_groups": 16,
|
86 |
"num_conv_pos_embeddings": 128,
|
87 |
"num_feat_extract_layers": 7,
|
88 |
"num_mel_bins": 80,
|
89 |
-
"num_speakers": 1,
|
90 |
"pad_token_id": 1,
|
91 |
"positional_dropout": 0.1,
|
92 |
-
"posterior_encoder_num_wavenet_layers": 16,
|
93 |
-
"prior_encoder_num_flows": 4,
|
94 |
-
"prior_encoder_num_wavenet_layers": 4,
|
95 |
"reduction_factor": 2,
|
96 |
-
"resblock_dilation_sizes": [
|
97 |
-
[
|
98 |
-
1,
|
99 |
-
3,
|
100 |
-
5
|
101 |
-
],
|
102 |
-
[
|
103 |
-
1,
|
104 |
-
3,
|
105 |
-
5
|
106 |
-
],
|
107 |
-
[
|
108 |
-
1,
|
109 |
-
3,
|
110 |
-
5
|
111 |
-
]
|
112 |
-
],
|
113 |
-
"resblock_kernel_sizes": [
|
114 |
-
3,
|
115 |
-
7,
|
116 |
-
11
|
117 |
-
],
|
118 |
-
"sampling_rate": 16000,
|
119 |
"scale_embedding": false,
|
120 |
"speaker_embedding_dim": 512,
|
121 |
-
"speaker_embedding_size": 0,
|
122 |
-
"speaking_rate": 1.0,
|
123 |
-
"spectrogram_bins": 513,
|
124 |
"speech_decoder_postnet_dropout": 0.5,
|
125 |
"speech_decoder_postnet_kernel": 5,
|
126 |
"speech_decoder_postnet_layers": 5,
|
@@ -130,26 +86,7 @@
|
|
130 |
"speech_decoder_prenet_units": 256,
|
131 |
"torch_dtype": "float32",
|
132 |
"transformers_version": "4.35.2",
|
133 |
-
"upsample_initial_channel": 512,
|
134 |
-
"upsample_kernel_sizes": [
|
135 |
-
16,
|
136 |
-
16,
|
137 |
-
4,
|
138 |
-
4
|
139 |
-
],
|
140 |
-
"upsample_rates": [
|
141 |
-
8,
|
142 |
-
8,
|
143 |
-
2,
|
144 |
-
2
|
145 |
-
],
|
146 |
-
"use_bias": true,
|
147 |
"use_cache": false,
|
148 |
"use_guided_attention_loss": true,
|
149 |
-
"
|
150 |
-
"vocab_size": 95,
|
151 |
-
"wavenet_dilation_rate": 1,
|
152 |
-
"wavenet_dropout": 0.0,
|
153 |
-
"wavenet_kernel_size": 5,
|
154 |
-
"window_size": 4
|
155 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/speecht5_tts",
|
3 |
"activation_dropout": 0.1,
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
|
|
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,
|
|
|
86 |
"speech_decoder_prenet_units": 256,
|
87 |
"torch_dtype": "float32",
|
88 |
"transformers_version": "4.35.2",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
"use_cache": false,
|
90 |
"use_guided_attention_loss": true,
|
91 |
+
"vocab_size": 81
|
|
|
|
|
|
|
|
|
|
|
92 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e9a8ed04ba0fc2d1c16e528ae034a4371e416cff28e5ed277afcb1ccf82283b
|
3 |
+
size 577789320
|
runs/Jan18_11-52-35_71565f425e09/events.out.tfevents.1705578756.71565f425e09.1122.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63e30dd6de25685876d87e9f680b3b91a8870d850d8e2b87f3e62e41833d9019
|
3 |
+
size 6917
|
tokenizer_config.json
CHANGED
@@ -59,5 +59,6 @@
|
|
59 |
"processor_class": "SpeechT5Processor",
|
60 |
"sp_model_kwargs": {},
|
61 |
"tokenizer_class": "SpeechT5Tokenizer",
|
|
|
62 |
"unk_token": "<unk>"
|
63 |
}
|
|
|
59 |
"processor_class": "SpeechT5Processor",
|
60 |
"sp_model_kwargs": {},
|
61 |
"tokenizer_class": "SpeechT5Tokenizer",
|
62 |
+
"trust_remote_code": false,
|
63 |
"unk_token": "<unk>"
|
64 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3545375cd1e95128155f1f4cc6c3d17df840b2a952535b7cd8b2ef2714a0550
|
3 |
size 4792
|