Hugging Face's logo

smtiitm
/
FastSpeech2_HS_latest_models

tts
indictts
fs2
mfa
HS
hybrid_segmentation
fastspeech2
Model card Files
xet
Community
2
utkarsh2299 commited on
Commit
5dd2edf
·
verified ·
1 Parent(s): 2e42c24

Upload 12 files

Browse files
Files changed (12) hide show
  1. punjabi_latest/female/model/config.yaml +315 -0
  2. punjabi_latest/female/model/energy_stats.npz +3 -0
  3. punjabi_latest/female/model/feats_stats.npz +3 -0
  4. punjabi_latest/female/model/feats_type +1 -0
  5. punjabi_latest/female/model/model.pth +3 -0
  6. punjabi_latest/female/model/pitch_stats.npz +3 -0
  7. punjabi_latest/male/model/config.yaml +319 -0
  8. punjabi_latest/male/model/energy_stats.npz +3 -0
  9. punjabi_latest/male/model/feats_stats.npz +3 -0
  10. punjabi_latest/male/model/feats_type +1 -0
  11. punjabi_latest/male/model/model.pth +3 -0
  12. punjabi_latest/male/model/pitch_stats.npz +3 -0
punjabi_latest/female/model/config.yaml ADDED
@@ -0,0 +1,315 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config: conf/tuning/train_fastspeech2.yaml
2
+ print_config: false
3
+ log_level: INFO
4
+ drop_last_iter: false
5
+ dry_run: false
6
+ iterator_type: sequence
7
+ valid_iterator_type: null
8
+ output_dir: exp/tts_train_fastspeech2_raw_char_None
9
+ ngpu: 1
10
+ seed: 0
11
+ num_workers: 1
12
+ num_att_plot: 3
13
+ dist_backend: nccl
14
+ dist_init_method: env://
15
+ dist_world_size: 2
16
+ dist_rank: 0
17
+ local_rank: 0
18
+ dist_master_addr: localhost
19
+ dist_master_port: 45599
20
+ dist_launcher: null
21
+ multiprocessing_distributed: true
22
+ unused_parameters: false
23
+ sharded_ddp: false
24
+ cudnn_enabled: true
25
+ cudnn_benchmark: false
26
+ cudnn_deterministic: true
27
+ collect_stats: false
28
+ write_collected_feats: false
29
+ max_epoch: 1000
30
+ patience: null
31
+ val_scheduler_criterion:
32
+ - valid
33
+ - loss
34
+ early_stopping_criterion:
35
+ - valid
36
+ - loss
37
+ - min
38
+ best_model_criterion:
39
+ - - valid
40
+ - loss
41
+ - min
42
+ - - train
43
+ - loss
44
+ - min
45
+ keep_nbest_models: 5
46
+ nbest_averaging_interval: 0
47
+ grad_clip: 1.0
48
+ grad_clip_type: 2.0
49
+ grad_noise: false
50
+ accum_grad: 8
51
+ no_forward_run: false
52
+ resume: true
53
+ train_dtype: float32
54
+ use_amp: false
55
+ log_interval: null
56
+ use_matplotlib: true
57
+ use_tensorboard: true
58
+ create_graph_in_tensorboard: false
59
+ use_wandb: false
60
+ wandb_project: null
61
+ wandb_id: null
62
+ wandb_entity: null
63
+ wandb_name: null
64
+ wandb_model_log_interval: -1
65
+ detect_anomaly: false
66
+ use_adapter: false
67
+ adapter: lora
68
+ save_strategy: all
69
+ adapter_conf: {}
70
+ pretrain_path: null
71
+ init_param: []
72
+ ignore_init_mismatch: false
73
+ freeze_param: []
74
+ num_iters_per_epoch: 800
75
+ batch_size: 20
76
+ valid_batch_size: null
77
+ batch_bins: 3000000
78
+ valid_batch_bins: null
79
+ train_shape_file:
80
+ - exp/tts_stats_raw_char_None/train/text_shape.char
81
+ - exp/tts_stats_raw_char_None/train/speech_shape
82
+ valid_shape_file:
83
+ - exp/tts_stats_raw_char_None/valid/text_shape.char
84
+ - exp/tts_stats_raw_char_None/valid/speech_shape
85
+ batch_type: numel
86
+ valid_batch_type: null
87
+ fold_length:
88
+ - 150
89
+ - 819200
90
+ sort_in_batch: descending
91
+ shuffle_within_batch: false
92
+ sort_batch: descending
93
+ multiple_iterator: false
94
+ chunk_length: 500
95
+ chunk_shift_ratio: 0.5
96
+ num_cache_chunks: 1024
97
+ chunk_excluded_key_prefixes: []
98
+ chunk_default_fs: null
99
+ chunk_max_abs_length: null
100
+ chunk_discard_short_samples: true
101
+ train_data_path_and_name_and_type:
102
+ - - dump/raw/tr_no_dev/text
103
+ - text
104
+ - text
105
+ - - duration_info/tr_no_dev/durations
106
+ - durations
107
+ - text_int
108
+ - - dump/raw/tr_no_dev/wav.scp
109
+ - speech
110
+ - sound
111
+ - - exp/tts_stats_raw_char_None/train/collect_feats/pitch.scp
112
+ - pitch
113
+ - npy
114
+ - - exp/tts_stats_raw_char_None/train/collect_feats/energy.scp
115
+ - energy
116
+ - npy
117
+ valid_data_path_and_name_and_type:
118
+ - - dump/raw/dev/text
119
+ - text
120
+ - text
121
+ - - duration_info/dev/durations
122
+ - durations
123
+ - text_int
124
+ - - dump/raw/dev/wav.scp
125
+ - speech
126
+ - sound
127
+ - - exp/tts_stats_raw_char_None/valid/collect_feats/pitch.scp
128
+ - pitch
129
+ - npy
130
+ - - exp/tts_stats_raw_char_None/valid/collect_feats/energy.scp
131
+ - energy
132
+ - npy
133
+ allow_variable_data_keys: false
134
+ max_cache_size: 0.0
135
+ max_cache_fd: 32
136
+ allow_multi_rates: false
137
+ valid_max_cache_size: null
138
+ exclude_weight_decay: false
139
+ exclude_weight_decay_conf: {}
140
+ optim: adam
141
+ optim_conf:
142
+ lr: 1.0
143
+ scheduler: noamlr
144
+ scheduler_conf:
145
+ model_size: 384
146
+ warmup_steps: 4000
147
+ token_list:
148
+ - <blank>
149
+ - <unk>
150
+ - <space>
151
+ - $
152
+ - ','
153
+ - .
154
+ - M
155
+ - q
156
+ - H
157
+ - k
158
+ - ख
159
+ - g
160
+ - घ
161
+ - ङ
162
+ - c
163
+ - C
164
+ - j
165
+ - J
166
+ - ञ
167
+ - ट
168
+ - ठ
169
+ - ड
170
+ - ढ
171
+ - ण
172
+ - t
173
+ - थ
174
+ - d
175
+ - ध
176
+ - n
177
+ - ऩ
178
+ - p
179
+ - P
180
+ - b
181
+ - B
182
+ - m
183
+ - y
184
+ - r
185
+ - ऱ
186
+ - l
187
+ - ള
188
+ - Z
189
+ - w
190
+ - श
191
+ - ष
192
+ - s
193
+ - h
194
+ - Y
195
+ - ऽ
196
+ - क
197
+ - K
198
+ - G
199
+ - z
200
+ - D
201
+ - T
202
+ - f
203
+ - ॠ
204
+ - ൺ
205
+ - N
206
+ - ർ
207
+ - ൽ
208
+ - ൾ
209
+ - a
210
+ - A
211
+ - i
212
+ - I
213
+ - u
214
+ - U
215
+ - R
216
+ - ऍ
217
+ - e
218
+ - E
219
+ - ऐ
220
+ - ऑ
221
+ - o
222
+ - O
223
+ - औ
224
+ - உ
225
+ - <sos/eos>
226
+ odim: null
227
+ model_conf: {}
228
+ use_preprocessor: true
229
+ token_type: char
230
+ bpemodel: null
231
+ non_linguistic_symbols: null
232
+ cleaner: null
233
+ g2p: null
234
+ feats_extract: fbank
235
+ feats_extract_conf:
236
+ n_fft: 8192
237
+ hop_length: 1024
238
+ win_length: 4096
239
+ fs: 48000
240
+ fmin: 0
241
+ fmax: 24000
242
+ n_mels: 160
243
+ normalize: global_mvn
244
+ normalize_conf:
245
+ stats_file: exp/tts_stats_raw_char_None/train/feats_stats.npz
246
+ tts: fastspeech2
247
+ tts_conf:
248
+ adim: 384
249
+ aheads: 2
250
+ elayers: 4
251
+ eunits: 1536
252
+ dlayers: 4
253
+ dunits: 1536
254
+ positionwise_layer_type: conv1d
255
+ positionwise_conv_kernel_size: 3
256
+ duration_predictor_layers: 2
257
+ duration_predictor_chans: 256
258
+ duration_predictor_kernel_size: 3
259
+ postnet_layers: 5
260
+ postnet_filts: 5
261
+ postnet_chans: 256
262
+ use_masking: true
263
+ use_scaled_pos_enc: true
264
+ encoder_normalize_before: true
265
+ decoder_normalize_before: true
266
+ reduction_factor: 1
267
+ init_type: xavier_uniform
268
+ init_enc_alpha: 1.0
269
+ init_dec_alpha: 1.0
270
+ transformer_enc_dropout_rate: 0.2
271
+ transformer_enc_positional_dropout_rate: 0.2
272
+ transformer_enc_attn_dropout_rate: 0.2
273
+ transformer_dec_dropout_rate: 0.2
274
+ transformer_dec_positional_dropout_rate: 0.2
275
+ transformer_dec_attn_dropout_rate: 0.2
276
+ pitch_predictor_layers: 5
277
+ pitch_predictor_chans: 256
278
+ pitch_predictor_kernel_size: 5
279
+ pitch_predictor_dropout: 0.5
280
+ pitch_embed_kernel_size: 1
281
+ pitch_embed_dropout: 0.0
282
+ stop_gradient_from_pitch_predictor: true
283
+ energy_predictor_layers: 2
284
+ energy_predictor_chans: 256
285
+ energy_predictor_kernel_size: 3
286
+ energy_predictor_dropout: 0.5
287
+ energy_embed_kernel_size: 1
288
+ energy_embed_dropout: 0.0
289
+ stop_gradient_from_energy_predictor: false
290
+ pitch_extract: dio
291
+ pitch_extract_conf:
292
+ fs: 48000
293
+ n_fft: 8192
294
+ hop_length: 1024
295
+ f0max: 400
296
+ f0min: 80
297
+ reduction_factor: 1
298
+ pitch_normalize: global_mvn
299
+ pitch_normalize_conf:
300
+ stats_file: exp/tts_stats_raw_char_None/train/pitch_stats.npz
301
+ energy_extract: energy
302
+ energy_extract_conf:
303
+ fs: 48000
304
+ n_fft: 8192
305
+ hop_length: 1024
306
+ win_length: 4096
307
+ reduction_factor: 1
308
+ energy_normalize: global_mvn
309
+ energy_normalize_conf:
310
+ stats_file: exp/tts_stats_raw_char_None/train/energy_stats.npz
311
+ required:
312
+ - output_dir
313
+ - token_list
314
+ version: '202402'
315
+ distributed: true
punjabi_latest/female/model/energy_stats.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6bc915e07125a441c1331d9d8055688ebfefef3e377fa9d83d2f0e3f239e59
3
+ size 770
punjabi_latest/female/model/feats_stats.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b51a82bc8431f31cb26c16a10e920cd9d48ece5b3f5a0964cd95b0201f06391
3
+ size 2042
punjabi_latest/female/model/feats_type ADDED
@@ -0,0 +1 @@
 
 
1
+ raw
punjabi_latest/female/model/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede8cf91cbbe639a621568b11eced54cdf44f3fd9a3e04f84e612069ad262dad
3
+ size 152128410
punjabi_latest/female/model/pitch_stats.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae45737310f98a7f83fd81d3b22eb02a513386a814d7f6fcde0cbf55f254828
3
+ size 770
punjabi_latest/male/model/config.yaml ADDED
@@ -0,0 +1,319 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ accum_grad: 8
2
+ adapter: lora
3
+ adapter_conf: {}
4
+ allow_multi_rates: false
5
+ allow_variable_data_keys: false
6
+ batch_bins: 3000000
7
+ batch_size: 20
8
+ batch_type: numel
9
+ best_model_criterion:
10
+ - - valid
11
+ - loss
12
+ - min
13
+ - - train
14
+ - loss
15
+ - min
16
+ bpemodel: null
17
+ chunk_default_fs: null
18
+ chunk_discard_short_samples: true
19
+ chunk_excluded_key_prefixes: []
20
+ chunk_length: 500
21
+ chunk_max_abs_length: null
22
+ chunk_shift_ratio: 0.5
23
+ cleaner: null
24
+ collect_stats: false
25
+ config: conf/tuning/train_fastspeech2.yaml
26
+ create_graph_in_tensorboard: false
27
+ cudnn_benchmark: false
28
+ cudnn_deterministic: true
29
+ cudnn_enabled: true
30
+ deepspeed_config: null
31
+ detect_anomaly: false
32
+ dist_backend: nccl
33
+ dist_init_method: env://
34
+ dist_launcher: null
35
+ dist_master_addr: localhost
36
+ dist_master_port: 59315
37
+ dist_rank: 0
38
+ dist_world_size: 2
39
+ distributed: true
40
+ drop_last_iter: false
41
+ dry_run: false
42
+ early_stopping_criterion:
43
+ - valid
44
+ - loss
45
+ - min
46
+ energy_extract: energy
47
+ energy_extract_conf:
48
+ fs: 48000
49
+ hop_length: 1024
50
+ n_fft: 8192
51
+ reduction_factor: 1
52
+ win_length: 4096
53
+ energy_normalize: global_mvn
54
+ energy_normalize_conf:
55
+ stats_file: /home/speech/Fastspeech2_latest models/Fastspeech2_HS/punjabi_latest/male/model/energy_stats.npz
56
+ exclude_weight_decay: false
57
+ exclude_weight_decay_conf: {}
58
+ feats_extract: fbank
59
+ feats_extract_conf:
60
+ fmax: 24000
61
+ fmin: 0
62
+ fs: 48000
63
+ hop_length: 1024
64
+ n_fft: 8192
65
+ n_mels: 160
66
+ win_length: 4096
67
+ fold_length:
68
+ - 150
69
+ - 819200
70
+ freeze_param: []
71
+ g2p: null
72
+ grad_clip: 1.0
73
+ grad_clip_type: 2.0
74
+ grad_noise: false
75
+ ignore_init_mismatch: false
76
+ init_param: []
77
+ iterator_type: sequence
78
+ keep_nbest_models: 5
79
+ local_rank: 0
80
+ log_interval: null
81
+ log_level: INFO
82
+ max_cache_fd: 32
83
+ max_cache_size: 0.0
84
+ max_epoch: 1000
85
+ model_conf: {}
86
+ multi_task_dataset: false
87
+ multiple_iterator: false
88
+ multiprocessing_distributed: true
89
+ nbest_averaging_interval: 0
90
+ ngpu: 1
91
+ no_forward_run: false
92
+ non_linguistic_symbols: null
93
+ normalize: global_mvn
94
+ normalize_conf:
95
+ stats_file: /home/speech/Fastspeech2_latest models/Fastspeech2_HS/punjabi_latest/male/model/feats_stats.npz
96
+ num_att_plot: 3
97
+ num_cache_chunks: 1024
98
+ num_iters_per_epoch: 800
99
+ num_workers: 1
100
+ odim: null
101
+ optim: adam
102
+ optim_conf:
103
+ lr: 1.0
104
+ output_dir: exp/tts_train_fastspeech2_raw_char_None
105
+ patience: null
106
+ pitch_extract: dio
107
+ pitch_extract_conf:
108
+ f0max: 350
109
+ f0min: 40
110
+ fs: 48000
111
+ hop_length: 1024
112
+ n_fft: 8192
113
+ reduction_factor: 1
114
+ pitch_normalize: global_mvn
115
+ pitch_normalize_conf:
116
+ stats_file: /home/speech/Fastspeech2_latest models/Fastspeech2_HS/punjabi_latest/male/model/pitch_stats.npz
117
+ pretrain_path: null
118
+ print_config: false
119
+ required:
120
+ - output_dir
121
+ - token_list
122
+ resume: true
123
+ save_strategy: all
124
+ scheduler: noamlr
125
+ scheduler_conf:
126
+ model_size: 384
127
+ warmup_steps: 4000
128
+ seed: 0
129
+ sharded_ddp: false
130
+ shuffle_within_batch: false
131
+ sort_batch: descending
132
+ sort_in_batch: descending
133
+ token_list:
134
+ - <blank>
135
+ - <unk>
136
+ - <space>
137
+ - $
138
+ - ','
139
+ - .
140
+ - M
141
+ - q
142
+ - H
143
+ - k
144
+ - "\u0916"
145
+ - g
146
+ - "\u0918"
147
+ - "\u0919"
148
+ - c
149
+ - C
150
+ - j
151
+ - J
152
+ - "\u091E"
153
+ - "\u091F"
154
+ - "\u0920"
155
+ - "\u0921"
156
+ - "\u0922"
157
+ - "\u0923"
158
+ - t
159
+ - "\u0925"
160
+ - d
161
+ - "\u0927"
162
+ - n
163
+ - "\u0929"
164
+ - p
165
+ - P
166
+ - b
167
+ - B
168
+ - m
169
+ - y
170
+ - r
171
+ - "\u0931"
172
+ - l
173
+ - "\u0D33"
174
+ - Z
175
+ - w
176
+ - "\u0936"
177
+ - "\u0937"
178
+ - s
179
+ - h
180
+ - Y
181
+ - "\u093D"
182
+ - "\u0915"
183
+ - K
184
+ - G
185
+ - z
186
+ - D
187
+ - T
188
+ - f
189
+ - "\u0960"
190
+ - "\u0D7A"
191
+ - N
192
+ - "\u0D7C"
193
+ - "\u0D7D"
194
+ - "\u0D7E"
195
+ - a
196
+ - A
197
+ - i
198
+ - I
199
+ - u
200
+ - U
201
+ - R
202
+ - "\u090D"
203
+ - e
204
+ - E
205
+ - "\u0910"
206
+ - "\u0911"
207
+ - o
208
+ - O
209
+ - "\u0914"
210
+ - "\u0B89"
211
+ - <sos/eos>
212
+ token_type: char
213
+ train_data_path_and_name_and_type:
214
+ - - dump/raw/tr_no_dev/text
215
+ - text
216
+ - text
217
+ - - duration_info/tr_no_dev/durations
218
+ - durations
219
+ - text_int
220
+ - - dump/raw/tr_no_dev/wav.scp
221
+ - speech
222
+ - sound
223
+ - - exp/tts_stats_raw_char_None/train/collect_feats/pitch.scp
224
+ - pitch
225
+ - npy
226
+ - - exp/tts_stats_raw_char_None/train/collect_feats/energy.scp
227
+ - energy
228
+ - npy
229
+ train_dtype: float32
230
+ train_shape_file:
231
+ - exp/tts_stats_raw_char_None/train/text_shape.char
232
+ - exp/tts_stats_raw_char_None/train/speech_shape
233
+ tts: fastspeech2
234
+ tts_conf:
235
+ adim: 384
236
+ aheads: 2
237
+ decoder_normalize_before: true
238
+ dlayers: 4
239
+ dunits: 1536
240
+ duration_predictor_chans: 256
241
+ duration_predictor_kernel_size: 3
242
+ duration_predictor_layers: 2
243
+ elayers: 4
244
+ encoder_normalize_before: true
245
+ energy_embed_dropout: 0.0
246
+ energy_embed_kernel_size: 1
247
+ energy_predictor_chans: 256
248
+ energy_predictor_dropout: 0.5
249
+ energy_predictor_kernel_size: 3
250
+ energy_predictor_layers: 2
251
+ eunits: 1536
252
+ init_dec_alpha: 1.0
253
+ init_enc_alpha: 1.0
254
+ init_type: xavier_uniform
255
+ pitch_embed_dropout: 0.0
256
+ pitch_embed_kernel_size: 1
257
+ pitch_predictor_chans: 256
258
+ pitch_predictor_dropout: 0.5
259
+ pitch_predictor_kernel_size: 5
260
+ pitch_predictor_layers: 5
261
+ positionwise_conv_kernel_size: 3
262
+ positionwise_layer_type: conv1d
263
+ postnet_chans: 256
264
+ postnet_filts: 5
265
+ postnet_layers: 5
266
+ reduction_factor: 1
267
+ stop_gradient_from_energy_predictor: false
268
+ stop_gradient_from_pitch_predictor: true
269
+ transformer_dec_attn_dropout_rate: 0.2
270
+ transformer_dec_dropout_rate: 0.2
271
+ transformer_dec_positional_dropout_rate: 0.2
272
+ transformer_enc_attn_dropout_rate: 0.2
273
+ transformer_enc_dropout_rate: 0.2
274
+ transformer_enc_positional_dropout_rate: 0.2
275
+ use_masking: true
276
+ use_scaled_pos_enc: true
277
+ unused_parameters: false
278
+ use_adapter: false
279
+ use_amp: false
280
+ use_deepspeed: false
281
+ use_matplotlib: true
282
+ use_preprocessor: true
283
+ use_tensorboard: true
284
+ use_tf32: false
285
+ use_wandb: false
286
+ val_scheduler_criterion:
287
+ - valid
288
+ - loss
289
+ valid_batch_bins: null
290
+ valid_batch_size: null
291
+ valid_batch_type: null
292
+ valid_data_path_and_name_and_type:
293
+ - - dump/raw/dev/text
294
+ - text
295
+ - text
296
+ - - duration_info/dev/durations
297
+ - durations
298
+ - text_int
299
+ - - dump/raw/dev/wav.scp
300
+ - speech
301
+ - sound
302
+ - - exp/tts_stats_raw_char_None/valid/collect_feats/pitch.scp
303
+ - pitch
304
+ - npy
305
+ - - exp/tts_stats_raw_char_None/valid/collect_feats/energy.scp
306
+ - energy
307
+ - npy
308
+ valid_iterator_type: null
309
+ valid_max_cache_size: null
310
+ valid_shape_file:
311
+ - exp/tts_stats_raw_char_None/valid/text_shape.char
312
+ - exp/tts_stats_raw_char_None/valid/speech_shape
313
+ version: '202402'
314
+ wandb_entity: null
315
+ wandb_id: null
316
+ wandb_model_log_interval: -1
317
+ wandb_name: null
318
+ wandb_project: null
319
+ write_collected_feats: false
punjabi_latest/male/model/energy_stats.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7739f113c35af803bfed26b246efe8b2af520b13c40ae4c8c18a3b98ad5b40d7
3
+ size 770
punjabi_latest/male/model/feats_stats.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ee6c46dcdef0d592dc57879c746c20ba9e090d4317a5da52f0b76bf73ace64
3
+ size 2042
punjabi_latest/male/model/feats_type ADDED
@@ -0,0 +1 @@
 
 
1
+ raw
punjabi_latest/male/model/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110eb19c4f58f6b77f63d2c6e50b8165bee691b2f3707c3c2173a46069d233f4
3
+ size 152129434
punjabi_latest/male/model/pitch_stats.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa6db00b80b9671970c03ab13588fa388398b88d1331e9a42c637c5e6df4600
3
+ size 770