Commit
·
021c283
1
Parent(s):
4506bbf
Upload folder using huggingface_hub
Browse files
data/fa_token_list/bpe_unigram150/bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37973014e2648943c8039425244b075496461c86d8217375350fb35a79e2ddd5
|
| 3 |
+
size 239472
|
exp/asr_stats_raw_fa_bpe150_sp/train/feats_stats.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1250d7b3a4bdddb1f71734d4fb8a1c5657d039a5f9c1f08d298cfe525d8907d3
|
| 3 |
+
size 1402
|
exp/asr_train_asr_rnn_raw_fa_bpe150_sp/6epoch.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f730498097d77d754ce1111aab0a9218f57f277e98b05b8d3e23912b2d4ce91b
|
| 3 |
+
size 447981362
|
exp/asr_train_asr_rnn_raw_fa_bpe150_sp/config.yaml
ADDED
|
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
config: conf/tuning/train_asr_rnn.yaml
|
| 2 |
+
print_config: false
|
| 3 |
+
log_level: INFO
|
| 4 |
+
dry_run: false
|
| 5 |
+
iterator_type: sequence
|
| 6 |
+
output_dir: exp/asr_train_asr_rnn_raw_fa_bpe150_sp
|
| 7 |
+
ngpu: 1
|
| 8 |
+
seed: 0
|
| 9 |
+
num_workers: 1
|
| 10 |
+
num_att_plot: 3
|
| 11 |
+
dist_backend: nccl
|
| 12 |
+
dist_init_method: env://
|
| 13 |
+
dist_world_size: null
|
| 14 |
+
dist_rank: null
|
| 15 |
+
local_rank: 0
|
| 16 |
+
dist_master_addr: null
|
| 17 |
+
dist_master_port: null
|
| 18 |
+
dist_launcher: null
|
| 19 |
+
multiprocessing_distributed: false
|
| 20 |
+
unused_parameters: false
|
| 21 |
+
sharded_ddp: false
|
| 22 |
+
cudnn_enabled: true
|
| 23 |
+
cudnn_benchmark: false
|
| 24 |
+
cudnn_deterministic: true
|
| 25 |
+
collect_stats: false
|
| 26 |
+
write_collected_feats: false
|
| 27 |
+
max_epoch: 15
|
| 28 |
+
patience: 3
|
| 29 |
+
val_scheduler_criterion:
|
| 30 |
+
- valid
|
| 31 |
+
- loss
|
| 32 |
+
early_stopping_criterion:
|
| 33 |
+
- valid
|
| 34 |
+
- loss
|
| 35 |
+
- min
|
| 36 |
+
best_model_criterion:
|
| 37 |
+
- - train
|
| 38 |
+
- loss
|
| 39 |
+
- min
|
| 40 |
+
- - valid
|
| 41 |
+
- loss
|
| 42 |
+
- min
|
| 43 |
+
- - train
|
| 44 |
+
- acc
|
| 45 |
+
- max
|
| 46 |
+
- - valid
|
| 47 |
+
- acc
|
| 48 |
+
- max
|
| 49 |
+
keep_nbest_models:
|
| 50 |
+
- 10
|
| 51 |
+
nbest_averaging_interval: 0
|
| 52 |
+
grad_clip: 5.0
|
| 53 |
+
grad_clip_type: 2.0
|
| 54 |
+
grad_noise: false
|
| 55 |
+
accum_grad: 1
|
| 56 |
+
no_forward_run: false
|
| 57 |
+
resume: true
|
| 58 |
+
train_dtype: float32
|
| 59 |
+
use_amp: false
|
| 60 |
+
log_interval: null
|
| 61 |
+
use_matplotlib: true
|
| 62 |
+
use_tensorboard: true
|
| 63 |
+
use_wandb: false
|
| 64 |
+
wandb_project: null
|
| 65 |
+
wandb_id: null
|
| 66 |
+
wandb_entity: null
|
| 67 |
+
wandb_name: null
|
| 68 |
+
wandb_model_log_interval: -1
|
| 69 |
+
detect_anomaly: false
|
| 70 |
+
pretrain_path: null
|
| 71 |
+
init_param: []
|
| 72 |
+
ignore_init_mismatch: false
|
| 73 |
+
freeze_param: []
|
| 74 |
+
num_iters_per_epoch: null
|
| 75 |
+
batch_size: 30
|
| 76 |
+
valid_batch_size: null
|
| 77 |
+
batch_bins: 1000000
|
| 78 |
+
valid_batch_bins: null
|
| 79 |
+
train_shape_file:
|
| 80 |
+
- exp/asr_stats_raw_fa_bpe150_sp/train/speech_shape
|
| 81 |
+
- exp/asr_stats_raw_fa_bpe150_sp/train/text_shape.bpe
|
| 82 |
+
valid_shape_file:
|
| 83 |
+
- exp/asr_stats_raw_fa_bpe150_sp/valid/speech_shape
|
| 84 |
+
- exp/asr_stats_raw_fa_bpe150_sp/valid/text_shape.bpe
|
| 85 |
+
batch_type: folded
|
| 86 |
+
valid_batch_type: null
|
| 87 |
+
fold_length:
|
| 88 |
+
- 80000
|
| 89 |
+
- 150
|
| 90 |
+
sort_in_batch: descending
|
| 91 |
+
sort_batch: descending
|
| 92 |
+
multiple_iterator: false
|
| 93 |
+
chunk_length: 500
|
| 94 |
+
chunk_shift_ratio: 0.5
|
| 95 |
+
num_cache_chunks: 1024
|
| 96 |
+
train_data_path_and_name_and_type:
|
| 97 |
+
- - dump/raw/train_fa_sp/wav.scp
|
| 98 |
+
- speech
|
| 99 |
+
- sound
|
| 100 |
+
- - dump/raw/train_fa_sp/text
|
| 101 |
+
- text
|
| 102 |
+
- text
|
| 103 |
+
valid_data_path_and_name_and_type:
|
| 104 |
+
- - dump/raw/dev_fa/wav.scp
|
| 105 |
+
- speech
|
| 106 |
+
- sound
|
| 107 |
+
- - dump/raw/dev_fa/text
|
| 108 |
+
- text
|
| 109 |
+
- text
|
| 110 |
+
allow_variable_data_keys: false
|
| 111 |
+
max_cache_size: 0.0
|
| 112 |
+
max_cache_fd: 32
|
| 113 |
+
valid_max_cache_size: null
|
| 114 |
+
optim: adadelta
|
| 115 |
+
optim_conf:
|
| 116 |
+
lr: 0.1
|
| 117 |
+
scheduler: null
|
| 118 |
+
scheduler_conf: {}
|
| 119 |
+
token_list:
|
| 120 |
+
- <blank>
|
| 121 |
+
- <unk>
|
| 122 |
+
- ی
|
| 123 |
+
- ا
|
| 124 |
+
- ه
|
| 125 |
+
- ▁
|
| 126 |
+
- ر
|
| 127 |
+
- م
|
| 128 |
+
- و
|
| 129 |
+
- د
|
| 130 |
+
- ت
|
| 131 |
+
- ش
|
| 132 |
+
- ن
|
| 133 |
+
- ل
|
| 134 |
+
- ▁ب
|
| 135 |
+
- ز
|
| 136 |
+
- ب
|
| 137 |
+
- .
|
| 138 |
+
- ▁م
|
| 139 |
+
- ان
|
| 140 |
+
- ▁ا
|
| 141 |
+
- س
|
| 142 |
+
- ک
|
| 143 |
+
- ▁می
|
| 144 |
+
- گ
|
| 145 |
+
- ف
|
| 146 |
+
- ▁د
|
| 147 |
+
- ؟
|
| 148 |
+
- ق
|
| 149 |
+
- ▁و
|
| 150 |
+
- ید
|
| 151 |
+
- ▁ن
|
| 152 |
+
- ند
|
| 153 |
+
- ست
|
| 154 |
+
- ار
|
| 155 |
+
- ▁چ
|
| 156 |
+
- ع
|
| 157 |
+
- ج
|
| 158 |
+
- ▁ت
|
| 159 |
+
- ▁ک
|
| 160 |
+
- ▁با
|
| 161 |
+
- خ
|
| 162 |
+
- ون
|
| 163 |
+
- ▁پ
|
| 164 |
+
- ▁به
|
| 165 |
+
- ▁من
|
| 166 |
+
- ▁س
|
| 167 |
+
- ▁را
|
| 168 |
+
- ،
|
| 169 |
+
- ▁خ
|
| 170 |
+
- ▁این
|
| 171 |
+
- ▁کن
|
| 172 |
+
- ▁آ
|
| 173 |
+
- ▁در
|
| 174 |
+
- ای
|
| 175 |
+
- ▁از
|
| 176 |
+
- اد
|
| 177 |
+
- ▁است
|
| 178 |
+
- ح
|
| 179 |
+
- ص
|
| 180 |
+
- ▁ش
|
| 181 |
+
- ط
|
| 182 |
+
- ▁تو
|
| 183 |
+
- ین
|
| 184 |
+
- ▁دار
|
| 185 |
+
- ▁که
|
| 186 |
+
- ال
|
| 187 |
+
- ▁رو
|
| 188 |
+
- ▁گ
|
| 189 |
+
- ▁ج
|
| 190 |
+
- ور
|
| 191 |
+
- ام
|
| 192 |
+
- ▁هم
|
| 193 |
+
- ▁ح
|
| 194 |
+
- فت
|
| 195 |
+
- رد
|
| 196 |
+
- یم
|
| 197 |
+
- پ
|
| 198 |
+
- غ
|
| 199 |
+
- چ
|
| 200 |
+
- ذ
|
| 201 |
+
- ض
|
| 202 |
+
- ظ
|
| 203 |
+
- '!'
|
| 204 |
+
- ث
|
| 205 |
+
- ً
|
| 206 |
+
- ئ
|
| 207 |
+
- '"'
|
| 208 |
+
- ژ
|
| 209 |
+
- ك
|
| 210 |
+
- آ
|
| 211 |
+
- ي
|
| 212 |
+
- ':'
|
| 213 |
+
- ى
|
| 214 |
+
- '-'
|
| 215 |
+
- ِ
|
| 216 |
+
- أ
|
| 217 |
+
- َ
|
| 218 |
+
- »
|
| 219 |
+
- ـ
|
| 220 |
+
- ','
|
| 221 |
+
- ُ
|
| 222 |
+
- (
|
| 223 |
+
- )
|
| 224 |
+
- ء
|
| 225 |
+
- ٔ
|
| 226 |
+
- ٬
|
| 227 |
+
- ّ
|
| 228 |
+
- ؛
|
| 229 |
+
- B
|
| 230 |
+
- C
|
| 231 |
+
- A
|
| 232 |
+
- E
|
| 233 |
+
- G
|
| 234 |
+
- M
|
| 235 |
+
- S
|
| 236 |
+
- ؤ
|
| 237 |
+
- I
|
| 238 |
+
- ;
|
| 239 |
+
- T
|
| 240 |
+
- H
|
| 241 |
+
- _
|
| 242 |
+
- F
|
| 243 |
+
- D
|
| 244 |
+
- ۀ
|
| 245 |
+
- Y
|
| 246 |
+
- N
|
| 247 |
+
- K
|
| 248 |
+
- U
|
| 249 |
+
- –
|
| 250 |
+
- ٌ
|
| 251 |
+
- P
|
| 252 |
+
- O
|
| 253 |
+
- Q
|
| 254 |
+
- Z
|
| 255 |
+
- '&'
|
| 256 |
+
- L
|
| 257 |
+
- R
|
| 258 |
+
- ة
|
| 259 |
+
- X
|
| 260 |
+
- ā
|
| 261 |
+
- '#'
|
| 262 |
+
- “
|
| 263 |
+
- '='
|
| 264 |
+
- «
|
| 265 |
+
- š
|
| 266 |
+
- ْ
|
| 267 |
+
- ے
|
| 268 |
+
- ”
|
| 269 |
+
- <sos/eos>
|
| 270 |
+
init: null
|
| 271 |
+
input_size: null
|
| 272 |
+
ctc_conf:
|
| 273 |
+
dropout_rate: 0.0
|
| 274 |
+
ctc_type: builtin
|
| 275 |
+
reduce: true
|
| 276 |
+
ignore_nan_grad: true
|
| 277 |
+
joint_net_conf: null
|
| 278 |
+
model_conf:
|
| 279 |
+
ctc_weight: 0.5
|
| 280 |
+
use_preprocessor: true
|
| 281 |
+
token_type: bpe
|
| 282 |
+
bpemodel: data/fa_token_list/bpe_unigram150/bpe.model
|
| 283 |
+
non_linguistic_symbols: null
|
| 284 |
+
cleaner: null
|
| 285 |
+
g2p: null
|
| 286 |
+
speech_volume_normalize: null
|
| 287 |
+
rir_scp: null
|
| 288 |
+
rir_apply_prob: 1.0
|
| 289 |
+
noise_scp: null
|
| 290 |
+
noise_apply_prob: 1.0
|
| 291 |
+
noise_db_range: '13_15'
|
| 292 |
+
frontend: default
|
| 293 |
+
frontend_conf:
|
| 294 |
+
fs: 16k
|
| 295 |
+
specaug: specaug
|
| 296 |
+
specaug_conf:
|
| 297 |
+
apply_time_warp: true
|
| 298 |
+
time_warp_window: 5
|
| 299 |
+
time_warp_mode: bicubic
|
| 300 |
+
apply_freq_mask: true
|
| 301 |
+
freq_mask_width_range:
|
| 302 |
+
- 0
|
| 303 |
+
- 27
|
| 304 |
+
num_freq_mask: 2
|
| 305 |
+
apply_time_mask: true
|
| 306 |
+
time_mask_width_ratio_range:
|
| 307 |
+
- 0.0
|
| 308 |
+
- 0.05
|
| 309 |
+
num_time_mask: 2
|
| 310 |
+
normalize: global_mvn
|
| 311 |
+
normalize_conf:
|
| 312 |
+
stats_file: exp/asr_stats_raw_fa_bpe150_sp/train/feats_stats.npz
|
| 313 |
+
preencoder: null
|
| 314 |
+
preencoder_conf: {}
|
| 315 |
+
encoder: vgg_rnn
|
| 316 |
+
encoder_conf:
|
| 317 |
+
rnn_type: lstm
|
| 318 |
+
bidirectional: true
|
| 319 |
+
use_projection: true
|
| 320 |
+
num_layers: 4
|
| 321 |
+
hidden_size: 1024
|
| 322 |
+
output_size: 1024
|
| 323 |
+
postencoder: null
|
| 324 |
+
postencoder_conf: {}
|
| 325 |
+
decoder: rnn
|
| 326 |
+
decoder_conf:
|
| 327 |
+
num_layers: 2
|
| 328 |
+
hidden_size: 1024
|
| 329 |
+
sampling_probability: 0
|
| 330 |
+
att_conf:
|
| 331 |
+
atype: location
|
| 332 |
+
adim: 1024
|
| 333 |
+
aconv_chans: 10
|
| 334 |
+
aconv_filts: 100
|
| 335 |
+
required:
|
| 336 |
+
- output_dir
|
| 337 |
+
- token_list
|
| 338 |
+
version: 0.10.6a1
|
| 339 |
+
distributed: false
|
meta.yaml
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
espnet: 0.10.6a1
|
| 2 |
+
files:
|
| 3 |
+
asr_model_file: exp/asr_train_asr_rnn_raw_fa_bpe150_sp/6epoch.pth
|
| 4 |
+
python: "3.9.5 (default, Jun 4 2021, 12:28:51) \n[GCC 7.5.0]"
|
| 5 |
+
timestamp: 1651506588.805354
|
| 6 |
+
torch: 1.8.1+cu102
|
| 7 |
+
yaml_files:
|
| 8 |
+
asr_train_config: exp/asr_train_asr_rnn_raw_fa_bpe150_sp/config.yaml
|