Upload config.json with huggingface_hub
Browse files- config.json +21 -35
config.json
CHANGED
@@ -27,8 +27,8 @@
|
|
27 |
"batch_size": 32,
|
28 |
"eval_batch_size": 16,
|
29 |
"grad_clip": [
|
30 |
-
1000,
|
31 |
-
1000
|
32 |
],
|
33 |
"scheduler_after_epoch": true,
|
34 |
"lr": 0.001,
|
@@ -54,37 +54,12 @@
|
|
54 |
"use_noise_augment": false,
|
55 |
"audio": {
|
56 |
"fft_size": 1024,
|
|
|
57 |
"win_length": 1024,
|
58 |
"hop_length": 256,
|
59 |
-
"frame_shift_ms": null,
|
60 |
-
"frame_length_ms": null,
|
61 |
-
"stft_pad_mode": "reflect",
|
62 |
-
"sample_rate": 24000,
|
63 |
-
"resample": false,
|
64 |
-
"preemphasis": 0.0,
|
65 |
-
"ref_level_db": 20,
|
66 |
-
"do_sound_norm": false,
|
67 |
-
"log_func": "np.log10",
|
68 |
-
"do_trim_silence": true,
|
69 |
-
"trim_db": 45,
|
70 |
-
"do_rms_norm": false,
|
71 |
-
"db_level": null,
|
72 |
-
"power": 1.5,
|
73 |
-
"griffin_lim_iters": 60,
|
74 |
"num_mels": 80,
|
75 |
"mel_fmin": 0,
|
76 |
-
"mel_fmax": null
|
77 |
-
"spec_gain": 20,
|
78 |
-
"do_amp_to_db_linear": true,
|
79 |
-
"do_amp_to_db_mel": true,
|
80 |
-
"pitch_fmax": 640.0,
|
81 |
-
"pitch_fmin": 1.0,
|
82 |
-
"signal_norm": true,
|
83 |
-
"min_level_db": -100,
|
84 |
-
"symmetric_norm": true,
|
85 |
-
"max_norm": 4.0,
|
86 |
-
"clip_norm": true,
|
87 |
-
"stats_path": null
|
88 |
},
|
89 |
"use_phonemes": true,
|
90 |
"phonemizer": "espeak",
|
@@ -134,11 +109,21 @@
|
|
134 |
}
|
135 |
],
|
136 |
"test_sentences": [
|
137 |
-
[
|
138 |
-
|
139 |
-
|
140 |
-
[
|
141 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
142 |
],
|
143 |
"eval_split_max_size": null,
|
144 |
"eval_split_size": 0.01,
|
@@ -211,7 +196,7 @@
|
|
211 |
"use_sdp": true,
|
212 |
"noise_scale": 1.0,
|
213 |
"inference_noise_scale": 0.667,
|
214 |
-
"length_scale": 1,
|
215 |
"noise_scale_dp": 1.0,
|
216 |
"inference_noise_scale_dp": 1.0,
|
217 |
"max_inference_len": null,
|
@@ -276,5 +261,6 @@
|
|
276 |
"use_d_vector_file": false,
|
277 |
"d_vector_file": null,
|
278 |
"d_vector_dim": 0,
|
|
|
279 |
"github_branch": "inside_docker"
|
280 |
}
|
|
|
27 |
"batch_size": 32,
|
28 |
"eval_batch_size": 16,
|
29 |
"grad_clip": [
|
30 |
+
1000.0,
|
31 |
+
1000.0
|
32 |
],
|
33 |
"scheduler_after_epoch": true,
|
34 |
"lr": 0.001,
|
|
|
54 |
"use_noise_augment": false,
|
55 |
"audio": {
|
56 |
"fft_size": 1024,
|
57 |
+
"sample_rate": 24000,
|
58 |
"win_length": 1024,
|
59 |
"hop_length": 256,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
"num_mels": 80,
|
61 |
"mel_fmin": 0,
|
62 |
+
"mel_fmax": null
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
},
|
64 |
"use_phonemes": true,
|
65 |
"phonemizer": "espeak",
|
|
|
109 |
}
|
110 |
],
|
111 |
"test_sentences": [
|
112 |
+
[
|
113 |
+
"\u0633\u0644\u0637\u0627\u0646 \u0645\u062d\u0645\u0648\u062f \u062f\u0631 \u0632\u0645\u0633\u062a\u0627\u0646\u06cc \u0633\u062e\u062a \u0628\u0647 \u0637\u0644\u062e\u06a9 \u06af\u0641\u062a \u06a9\u0647: \u0628\u0627 \u0627\u06cc\u0646 \u062c\u0627\u0645\u0647 \u06cc \u06cc\u06a9 \u0644\u0627 \u062f\u0631 \u0627\u06cc\u0646 \u0633\u0631\u0645\u0627 \u0686\u0647 \u0645\u06cc \u06a9\u0646\u06cc "
|
114 |
+
],
|
115 |
+
[
|
116 |
+
"\u0645\u0631\u062f\u06cc \u0646\u0632\u062f \u0628\u0642\u0627\u0644\u06cc \u0622\u0645\u062f \u0648 \u06af\u0641\u062a \u067e\u06cc\u0627\u0632 \u0647\u0645 \u062f\u0647 \u062a\u0627 \u062f\u0647\u0627\u0646 \u0628\u062f\u0627\u0646 \u062e\u0648 \u0634\u0628\u0648\u06cc \u0633\u0627\u0632\u0645."
|
117 |
+
],
|
118 |
+
[
|
119 |
+
"\u0627\u0632 \u0645\u0627\u0644 \u062e\u0648\u062f \u067e\u0627\u0631\u0647 \u0627\u06cc \u06af\u0648\u0634\u062a \u0628\u0633\u062a\u0627\u0646 \u0648 \u0632\u06cc\u0631\u0647 \u0628\u0627\u06cc\u06cc \u0645\u0639\u0637\u0651\u0631 \u0628\u0633\u0627\u0632"
|
120 |
+
],
|
121 |
+
[
|
122 |
+
"\u06cc\u06a9 \u0628\u0627\u0631 \u0647\u0645 \u0627\u0632 \u062c\u0647\u0646\u0645 \u0628\u06af\u0648\u06cc\u06cc\u062f."
|
123 |
+
],
|
124 |
+
[
|
125 |
+
"\u06cc\u06a9\u06cc \u0627\u0633\u0628\u06cc \u0628\u0647 \u0639\u0627\u0631\u06cc\u062a \u062e\u0648\u0627\u0633\u062a"
|
126 |
+
]
|
127 |
],
|
128 |
"eval_split_max_size": null,
|
129 |
"eval_split_size": 0.01,
|
|
|
196 |
"use_sdp": true,
|
197 |
"noise_scale": 1.0,
|
198 |
"inference_noise_scale": 0.667,
|
199 |
+
"length_scale": 1.0,
|
200 |
"noise_scale_dp": 1.0,
|
201 |
"inference_noise_scale_dp": 1.0,
|
202 |
"max_inference_len": null,
|
|
|
261 |
"use_d_vector_file": false,
|
262 |
"d_vector_file": null,
|
263 |
"d_vector_dim": 0,
|
264 |
+
"restore_path": "/kaggle/working/train_output/kagg/best_model_1725.pth",
|
265 |
"github_branch": "inside_docker"
|
266 |
}
|