“siddhu001” commited on
Commit
310e414
1 Parent(s): e32c676

Update model

Browse files
README.md ADDED
@@ -0,0 +1,1358 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - espnet
4
+ - audio
5
+ - automatic-speech-recognition
6
+ language: en
7
+ datasets:
8
+ - slue-voxceleb
9
+ license: cc-by-4.0
10
+ ---
11
+
12
+ ## ESPnet2 ASR model
13
+
14
+ ### `espnet/sluevoxceleb_wavlm_complex_slu`
15
+
16
+ This model was trained by “siddhu001” using slue-voxceleb recipe in [espnet](https://github.com/espnet/espnet/).
17
+
18
+ ### Demo: How to use in ESPnet2
19
+
20
+ Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
21
+ if you haven't done that already.
22
+
23
+ ```bash
24
+ cd espnet
25
+ git checkout e23ef85f0b3116ad5c60d0833f186da0deec0734
26
+ pip install -e .
27
+ cd egs2/slue-voxceleb/slu1_correct
28
+ ./run.sh --skip_data_prep false --skip_train true --download_model espnet/sluevoxceleb_wavlm_complex_slu
29
+ ```
30
+
31
+ <!-- Generated by scripts/utils/show_asr_result.sh -->
32
+ # RESULTS
33
+ ## Environments
34
+ - date: `Sun Feb 11 12:27:01 CST 2024`
35
+ - python version: `3.9.13 (main, Aug 25 2022, 23:26:10) [GCC 11.2.0]`
36
+ - espnet version: `espnet 202310`
37
+ - pytorch version: `pytorch 2.1.0+cu121`
38
+ - Git hash: `21d2105784e4da98397bf487b2550d4c6e16d40d`
39
+ - Commit date: `Wed Jan 31 13:40:37 2024 -0600`
40
+
41
+ ## exp/slu_train_asr_raw_en_word_sp
42
+ ### WER
43
+
44
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
45
+ |---|---|---|---|---|---|---|---|---|
46
+ |decode_asr_ctc0.3_beam10_slu_model_valid.acc.ave_10best/test|3530|144908|90.8|6.2|3.0|2.8|12.0|88.9|
47
+ |decode_asr_ctc0.3_slu_model_valid.acc.ave_10best/test|3530|144908|90.1|6.3|3.6|2.9|12.8|89.1|
48
+ |decode_asr_slu_model_valid.acc.ave_10best/devel|1450|58104|91.5|5.5|3.0|2.5|11.0|85.9|
49
+ |decode_asr_slu_model_valid.acc.ave_10best/test|3530|144908|90.1|6.3|3.6|2.9|12.8|89.1|
50
+
51
+ ### CER
52
+
53
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
54
+ |---|---|---|---|---|---|---|---|---|
55
+ |decode_asr_ctc0.3_beam10_slu_model_valid.acc.ave_10best/test|3530|647097|95.6|1.9|2.5|2.6|7.0|88.9|
56
+ |decode_asr_ctc0.3_slu_model_valid.acc.ave_10best/test|3530|647097|95.0|1.9|3.1|2.7|7.7|89.1|
57
+ |decode_asr_slu_model_valid.acc.ave_10best/devel|1450|256305|95.8|1.7|2.5|2.4|6.6|85.9|
58
+ |decode_asr_slu_model_valid.acc.ave_10best/test|3530|647097|95.0|1.9|3.1|2.7|7.7|89.1|
59
+
60
+ ### TER
61
+
62
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
63
+ |---|---|---|---|---|---|---|---|---|
64
+ ## exp/slu_train_asr_raw_en_word_sp/decode_asr_ctc0.3_beam10_slu_model_valid.acc.ave_10best
65
+ ### WER
66
+
67
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
68
+ |---|---|---|---|---|---|---|---|---|
69
+ |org/devel|1451|58267|92.2|5.3|2.5|2.3|10.1|86.0|
70
+
71
+ ### CER
72
+
73
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
74
+ |---|---|---|---|---|---|---|---|---|
75
+ |org/devel|1451|256942|96.4|1.6|2.0|2.2|5.8|86.0|
76
+
77
+ ### TER
78
+
79
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
80
+ |---|---|---|---|---|---|---|---|---|
81
+ ## exp/slu_train_asr_raw_en_word_sp/decode_asr_slu_model_valid.acc.ave_10best
82
+ ### WER
83
+
84
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
85
+ |---|---|---|---|---|---|---|---|---|
86
+ |org/devel|1451|58267|91.5|5.6|3.0|2.6|11.1|85.9|
87
+
88
+ ### CER
89
+
90
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
91
+ |---|---|---|---|---|---|---|---|---|
92
+ |org/devel|1451|256942|95.8|1.7|2.5|2.4|6.6|85.9|
93
+
94
+ ### TER
95
+
96
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
97
+ |---|---|---|---|---|---|---|---|---|
98
+
99
+ ## ASR config
100
+
101
+ <details><summary>expand</summary>
102
+
103
+ ```
104
+ config: conf/train_asr.yaml
105
+ print_config: false
106
+ log_level: INFO
107
+ drop_last_iter: false
108
+ dry_run: false
109
+ iterator_type: sequence
110
+ valid_iterator_type: null
111
+ output_dir: exp/slu_train_asr_raw_en_word_sp
112
+ ngpu: 1
113
+ seed: 2022
114
+ num_workers: 2
115
+ num_att_plot: 3
116
+ dist_backend: nccl
117
+ dist_init_method: env://
118
+ dist_world_size: 4
119
+ dist_rank: 0
120
+ local_rank: 0
121
+ dist_master_addr: localhost
122
+ dist_master_port: 36647
123
+ dist_launcher: null
124
+ multiprocessing_distributed: true
125
+ unused_parameters: false
126
+ sharded_ddp: false
127
+ cudnn_enabled: true
128
+ cudnn_benchmark: false
129
+ cudnn_deterministic: true
130
+ collect_stats: false
131
+ write_collected_feats: false
132
+ max_epoch: 70
133
+ patience: null
134
+ val_scheduler_criterion:
135
+ - valid
136
+ - loss
137
+ early_stopping_criterion:
138
+ - valid
139
+ - loss
140
+ - min
141
+ best_model_criterion:
142
+ - - valid
143
+ - acc
144
+ - max
145
+ keep_nbest_models: 10
146
+ nbest_averaging_interval: 10
147
+ grad_clip: 5.0
148
+ grad_clip_type: 2.0
149
+ grad_noise: false
150
+ accum_grad: 1
151
+ no_forward_run: false
152
+ resume: true
153
+ train_dtype: float32
154
+ use_amp: false
155
+ log_interval: 100
156
+ use_matplotlib: true
157
+ use_tensorboard: true
158
+ create_graph_in_tensorboard: false
159
+ use_wandb: false
160
+ wandb_project: null
161
+ wandb_id: null
162
+ wandb_entity: null
163
+ wandb_name: null
164
+ wandb_model_log_interval: -1
165
+ detect_anomaly: false
166
+ use_lora: false
167
+ save_lora_only: true
168
+ lora_conf: {}
169
+ pretrain_path: null
170
+ init_param: []
171
+ ignore_init_mismatch: false
172
+ freeze_param:
173
+ - frontend.upstream
174
+ num_iters_per_epoch: null
175
+ batch_size: 20
176
+ valid_batch_size: null
177
+ batch_bins: 12000000
178
+ valid_batch_bins: null
179
+ train_shape_file:
180
+ - exp/slu_stats_raw_en_word_sp/train/speech_shape
181
+ - exp/slu_stats_raw_en_word_sp/train/text_shape.word
182
+ valid_shape_file:
183
+ - exp/slu_stats_raw_en_word_sp/valid/speech_shape
184
+ - exp/slu_stats_raw_en_word_sp/valid/text_shape.word
185
+ batch_type: numel
186
+ valid_batch_type: null
187
+ fold_length:
188
+ - 80000
189
+ - 150
190
+ sort_in_batch: descending
191
+ shuffle_within_batch: false
192
+ sort_batch: descending
193
+ multiple_iterator: false
194
+ chunk_length: 500
195
+ chunk_shift_ratio: 0.5
196
+ num_cache_chunks: 1024
197
+ chunk_excluded_key_prefixes: []
198
+ chunk_default_fs: null
199
+ train_data_path_and_name_and_type:
200
+ - - dump/raw/train_sp/wav.scp
201
+ - speech
202
+ - sound
203
+ - - dump/raw/train_sp/text
204
+ - text
205
+ - text
206
+ valid_data_path_and_name_and_type:
207
+ - - dump/raw/devel/wav.scp
208
+ - speech
209
+ - sound
210
+ - - dump/raw/devel/text
211
+ - text
212
+ - text
213
+ allow_variable_data_keys: false
214
+ max_cache_size: 0.0
215
+ max_cache_fd: 32
216
+ allow_multi_rates: false
217
+ valid_max_cache_size: null
218
+ exclude_weight_decay: false
219
+ exclude_weight_decay_conf: {}
220
+ optim: adam
221
+ optim_conf:
222
+ lr: 0.002
223
+ weight_decay: 1.0e-06
224
+ scheduler: warmuplr
225
+ scheduler_conf:
226
+ warmup_steps: 5000
227
+ token_list:
228
+ - <blank>
229
+ - <unk>
230
+ - ▁i
231
+ - ▁and
232
+ - ''''
233
+ - s
234
+ - ▁the
235
+ - ▁a
236
+ - ▁it
237
+ - Neutral
238
+ - ▁to
239
+ - ▁you
240
+ - ▁that
241
+ - ▁of
242
+ - ▁in
243
+ - ▁was
244
+ - ▁uh
245
+ - ▁know
246
+ - t
247
+ - ▁so
248
+ - ▁we
249
+ - ▁he
250
+ - ing
251
+ - ▁um
252
+ - ed
253
+ - m
254
+ - ▁like
255
+ - ▁is
256
+ - ▁but
257
+ - Positive
258
+ - y
259
+ - ▁just
260
+ - ▁they
261
+ - re
262
+ - ▁this
263
+ - ▁for
264
+ - ▁be
265
+ - ▁my
266
+ - er
267
+ - ▁with
268
+ - ▁on
269
+ - ▁think
270
+ - ▁p
271
+ - ▁have
272
+ - ▁she
273
+ - e
274
+ - ▁me
275
+ - ▁really
276
+ - ▁there
277
+ - ▁what
278
+ - ▁m
279
+ - a
280
+ - ▁do
281
+ - ▁all
282
+ - i
283
+ - al
284
+ - ve
285
+ - c
286
+ - ▁as
287
+ - ▁about
288
+ - ▁not
289
+ - ▁t
290
+ - n
291
+ - ▁at
292
+ - l
293
+ - ▁had
294
+ - ▁b
295
+ - ▁when
296
+ - ▁c
297
+ - g
298
+ - ar
299
+ - ▁out
300
+ - en
301
+ - ▁s
302
+ - ▁an
303
+ - ▁people
304
+ - or
305
+ - an
306
+ - d
307
+ - o
308
+ - ll
309
+ - ▁are
310
+ - in
311
+ - ▁very
312
+ - p
313
+ - b
314
+ - u
315
+ - ▁because
316
+ - es
317
+ - ▁can
318
+ - ▁don
319
+ - ▁or
320
+ - ▁up
321
+ - it
322
+ - ▁one
323
+ - ly
324
+ - ▁if
325
+ - ▁f
326
+ - st
327
+ - ▁were
328
+ - ▁mean
329
+ - ▁d
330
+ - ▁who
331
+ - ▁then
332
+ - ic
333
+ - 'on'
334
+ - ▁no
335
+ - ▁go
336
+ - ▁her
337
+ - ▁g
338
+ - ent
339
+ - ▁st
340
+ - ▁kind
341
+ - ri
342
+ - ▁would
343
+ - ▁get
344
+ - ▁e
345
+ - le
346
+ - at
347
+ - r
348
+ - ▁time
349
+ - ▁w
350
+ - ▁re
351
+ - h
352
+ - ▁from
353
+ - ▁l
354
+ - ▁said
355
+ - ▁him
356
+ - ▁how
357
+ - v
358
+ - ▁well
359
+ - ▁h
360
+ - ▁gonna
361
+ - ▁lot
362
+ - ▁see
363
+ - f
364
+ - ▁his
365
+ - et
366
+ - ion
367
+ - ▁been
368
+ - ▁great
369
+ - ▁yeah
370
+ - ▁love
371
+ - ▁which
372
+ - ▁got
373
+ - k
374
+ - ▁them
375
+ - ▁way
376
+ - id
377
+ - ▁show
378
+ - w
379
+ - ▁some
380
+ - ▁your
381
+ - ▁did
382
+ - ▁sort
383
+ - ▁has
384
+ - ▁things
385
+ - ▁back
386
+ - ▁where
387
+ - ▁something
388
+ - ir
389
+ - ▁thing
390
+ - ad
391
+ - ▁su
392
+ - ▁ch
393
+ - ▁n
394
+ - il
395
+ - as
396
+ - ▁j
397
+ - ▁more
398
+ - se
399
+ - ▁say
400
+ - ▁co
401
+ - nd
402
+ - ▁much
403
+ - ▁always
404
+ - ine
405
+ - ▁r
406
+ - ation
407
+ - ur
408
+ - ▁other
409
+ - th
410
+ - ▁
411
+ - ▁se
412
+ - ▁now
413
+ - ate
414
+ - ▁doing
415
+ - ▁work
416
+ - ow
417
+ - ▁could
418
+ - ally
419
+ - ▁these
420
+ - Negative
421
+ - ▁good
422
+ - ▁any
423
+ - ers
424
+ - ce
425
+ - ▁cause
426
+ - ▁ex
427
+ - ▁pro
428
+ - ▁little
429
+ - ▁actually
430
+ - ▁into
431
+ - ▁make
432
+ - ▁first
433
+ - ▁being
434
+ - ra
435
+ - ▁our
436
+ - ▁al
437
+ - ▁by
438
+ - ▁film
439
+ - ▁didn
440
+ - ▁v
441
+ - ct
442
+ - ity
443
+ - ch
444
+ - un
445
+ - ▁part
446
+ - ▁de
447
+ - ▁come
448
+ - is
449
+ - ie
450
+ - ▁right
451
+ - ▁o
452
+ - ▁off
453
+ - ol
454
+ - ▁two
455
+ - ▁never
456
+ - ▁le
457
+ - ot
458
+ - ut
459
+ - ▁movie
460
+ - ▁play
461
+ - ge
462
+ - ies
463
+ - el
464
+ - ▁con
465
+ - am
466
+ - ▁going
467
+ - ke
468
+ - ▁want
469
+ - im
470
+ - ▁feel
471
+ - ive
472
+ - ro
473
+ - ▁mo
474
+ - ▁different
475
+ - ck
476
+ - ▁life
477
+ - ist
478
+ - ▁oh
479
+ - all
480
+ - ▁lo
481
+ - ard
482
+ - ▁went
483
+ - and
484
+ - ▁sh
485
+ - ▁even
486
+ - ry
487
+ - ▁years
488
+ - ▁look
489
+ - ▁us
490
+ - ant
491
+ - ▁te
492
+ - ▁k
493
+ - ▁li
494
+ - ▁happen
495
+ - ure
496
+ - ▁their
497
+ - ▁those
498
+ - ▁take
499
+ - ment
500
+ - ▁day
501
+ - ble
502
+ - ast
503
+ - ▁every
504
+ - um
505
+ - ill
506
+ - op
507
+ - ▁thought
508
+ - ou
509
+ - us
510
+ - ay
511
+ - ▁th
512
+ - ▁put
513
+ - ▁story
514
+ - ▁new
515
+ - ▁down
516
+ - ish
517
+ - ▁big
518
+ - ▁wanna
519
+ - ▁ro
520
+ - ▁also
521
+ - ▁read
522
+ - ▁around
523
+ - ous
524
+ - ▁through
525
+ - red
526
+ - ▁came
527
+ - ▁character
528
+ - ess
529
+ - te
530
+ - ver
531
+ - ▁will
532
+ - ag
533
+ - ss
534
+ - ▁fun
535
+ - ▁over
536
+ - ▁many
537
+ - ▁bl
538
+ - ▁cl
539
+ - ▁man
540
+ - ▁than
541
+ - ▁pre
542
+ - ▁world
543
+ - ▁person
544
+ - z
545
+ - ▁sp
546
+ - ven
547
+ - ▁wanted
548
+ - ▁bit
549
+ - ▁before
550
+ - ▁mar
551
+ - one
552
+ - ab
553
+ - ▁en
554
+ - ci
555
+ - ▁set
556
+ - ▁ha
557
+ - ▁find
558
+ - ul
559
+ - ▁fi
560
+ - ▁end
561
+ - ▁un
562
+ - ▁sc
563
+ - ▁after
564
+ - ind
565
+ - ter
566
+ - ▁working
567
+ - ▁why
568
+ - om
569
+ - me
570
+ - ▁such
571
+ - ▁whole
572
+ - ▁kinda
573
+ - ne
574
+ - ▁bo
575
+ - x
576
+ - ▁most
577
+ - ▁ad
578
+ - ▁guy
579
+ - ▁spe
580
+ - ars
581
+ - ▁am
582
+ - ful
583
+ - ▁together
584
+ - ▁let
585
+ - ▁quite
586
+ - ain
587
+ - ▁everything
588
+ - ▁made
589
+ - ig
590
+ - ▁old
591
+ - able
592
+ - ▁tr
593
+ - ak
594
+ - ▁fo
595
+ - ▁po
596
+ - ore
597
+ - ice
598
+ - ▁real
599
+ - ▁knew
600
+ - ▁hard
601
+ - pp
602
+ - age
603
+ - ated
604
+ - ▁same
605
+ - ▁start
606
+ - ▁ever
607
+ - ning
608
+ - ▁watch
609
+ - art
610
+ - ▁again
611
+ - ▁here
612
+ - are
613
+ - ght
614
+ - ong
615
+ - ▁done
616
+ - ▁only
617
+ - ▁live
618
+ - ▁wasn
619
+ - ▁ho
620
+ - ▁u
621
+ - ▁maybe
622
+ - ▁need
623
+ - ▁everybody
624
+ - ust
625
+ - ans
626
+ - ▁three
627
+ - ▁having
628
+ - ▁music
629
+ - ack
630
+ - ld
631
+ - ▁trying
632
+ - ▁guys
633
+ - rou
634
+ - ach
635
+ - ving
636
+ - ▁tell
637
+ - ▁should
638
+ - ff
639
+ - ide
640
+ - ▁four
641
+ - ▁started
642
+ - ▁com
643
+ - ass
644
+ - ▁long
645
+ - ▁fe
646
+ - ▁course
647
+ - ▁called
648
+ - ▁own
649
+ - ress
650
+ - ▁moment
651
+ - ▁pl
652
+ - ▁still
653
+ - ▁anything
654
+ - ▁family
655
+ - ▁fin
656
+ - ▁dan
657
+ - ▁bro
658
+ - 'no'
659
+ - ther
660
+ - ▁per
661
+ - ▁amazing
662
+ - ▁stuff
663
+ - per
664
+ - ▁jo
665
+ - ▁certain
666
+ - os
667
+ - ▁talk
668
+ - ater
669
+ - ▁help
670
+ - ▁too
671
+ - ▁year
672
+ - ight
673
+ - ▁fa
674
+ - self
675
+ - ces
676
+ - ▁br
677
+ - ▁bet
678
+ - ▁someone
679
+ - ▁di
680
+ - ▁sing
681
+ - nt
682
+ - ick
683
+ - ▁ph
684
+ - row
685
+ - ▁script
686
+ - ▁remember
687
+ - ▁try
688
+ - qu
689
+ - ite
690
+ - ▁young
691
+ - ▁wh
692
+ - ▁ser
693
+ - ▁ask
694
+ - ▁book
695
+ - ▁each
696
+ - ▁wr
697
+ - ▁best
698
+ - ▁ag
699
+ - ▁women
700
+ - ose
701
+ - ions
702
+ - ved
703
+ - j
704
+ - ue
705
+ - ▁does
706
+ - ▁five
707
+ - ▁both
708
+ - ▁friends
709
+ - ▁act
710
+ - iz
711
+ - cess
712
+ - pt
713
+ - ▁somebody
714
+ - ft
715
+ - ▁nice
716
+ - ▁myself
717
+ - een
718
+ - fe
719
+ - sp
720
+ - ict
721
+ - ty
722
+ - ▁child
723
+ - ud
724
+ - pe
725
+ - ▁hope
726
+ - ▁fact
727
+ - ▁saying
728
+ - ave
729
+ - icul
730
+ - au
731
+ - ale
732
+ - ris
733
+ - ▁twenty
734
+ - ▁school
735
+ - ▁doesn
736
+ - ▁able
737
+ - pect
738
+ - ▁last
739
+ - ber
740
+ - ▁song
741
+ - od
742
+ - ▁str
743
+ - ▁interesting
744
+ - lf
745
+ - ▁em
746
+ - ▁wor
747
+ - ap
748
+ - og
749
+ - ▁ra
750
+ - ▁dis
751
+ - ▁coming
752
+ - ▁ab
753
+ - ▁house
754
+ - ▁next
755
+ - ▁tra
756
+ - ▁okay
757
+ - ere
758
+ - ary
759
+ - ▁incredi
760
+ - ▁car
761
+ - ▁job
762
+ - ▁used
763
+ - ▁give
764
+ - ▁god
765
+ - ▁americ
766
+ - ▁characters
767
+ - ▁app
768
+ - ▁walk
769
+ - ▁yes
770
+ - rew
771
+ - ▁getting
772
+ - ▁six
773
+ - ▁chan
774
+ - ▁ne
775
+ - ▁pretty
776
+ - ang
777
+ - ▁creat
778
+ - ▁another
779
+ - ▁ter
780
+ - ▁kids
781
+ - ▁felt
782
+ - ▁sometimes
783
+ - ▁place
784
+ - out
785
+ - ▁funny
786
+ - ase
787
+ - ich
788
+ - act
789
+ - ▁days
790
+ - ▁hum
791
+ - ▁bring
792
+ - ts
793
+ - ▁making
794
+ - ▁comp
795
+ - ▁become
796
+ - ute
797
+ - ▁wonderful
798
+ - ron
799
+ - les
800
+ - ▁saw
801
+ - ▁point
802
+ - ia
803
+ - ▁realiz
804
+ - ▁int
805
+ - ▁away
806
+ - ays
807
+ - ▁home
808
+ - ace
809
+ - ▁relationship
810
+ - ▁woman
811
+ - ▁everyone
812
+ - ▁comes
813
+ - ▁high
814
+ - dd
815
+ - ▁night
816
+ - ath
817
+ - ▁else
818
+ - vent
819
+ - ▁shoot
820
+ - vers
821
+ - day
822
+ - ▁sure
823
+ - ried
824
+ - ned
825
+ - ▁obviously
826
+ - ▁dra
827
+ - ▁inter
828
+ - co
829
+ - ▁playing
830
+ - ▁important
831
+ - ort
832
+ - uck
833
+ - ision
834
+ - pport
835
+ - ▁seen
836
+ - pl
837
+ - ▁fl
838
+ - ound
839
+ - ▁bas
840
+ - ull
841
+ - est
842
+ - ▁actor
843
+ - ▁lear
844
+ - ▁worked
845
+ - ▁believe
846
+ - ▁gen
847
+ - ▁keep
848
+ - ▁friend
849
+ - ▁sw
850
+ - ▁des
851
+ - ▁times
852
+ - ▁im
853
+ - ▁sur
854
+ - ▁sit
855
+ - ▁probably
856
+ - ok
857
+ - ▁took
858
+ - ep
859
+ - ough
860
+ - ip
861
+ - ood
862
+ - ▁sa
863
+ - ▁season
864
+ - vel
865
+ - wn
866
+ - ▁dec
867
+ - ▁excited
868
+ - ian
869
+ - ire
870
+ - ph
871
+ - ▁month
872
+ - ner
873
+ - ▁min
874
+ - ▁rel
875
+ - ating
876
+ - body
877
+ - ition
878
+ - ▁loved
879
+ - ▁aw
880
+ - ▁hear
881
+ - ple
882
+ - ▁cool
883
+ - ▁y
884
+ - ord
885
+ - our
886
+ - ▁game
887
+ - ms
888
+ - ub
889
+ - ▁might
890
+ - ▁kid
891
+ - ▁movies
892
+ - ical
893
+ - ▁bad
894
+ - ▁scene
895
+ - iv
896
+ - ▁enough
897
+ - ▁sm
898
+ - bly
899
+ - ▁fift
900
+ - ▁eight
901
+ - ▁experience
902
+ - ▁actors
903
+ - ▁cou
904
+ - ▁understand
905
+ - ▁week
906
+ - ▁few
907
+ - gin
908
+ - ting
909
+ - ▁director
910
+ - ▁almost
911
+ - ▁open
912
+ - ren
913
+ - ▁star
914
+ - ▁room
915
+ - ▁call
916
+ - oy
917
+ - ▁goes
918
+ - ▁told
919
+ - ▁once
920
+ - ▁found
921
+ - arly
922
+ - ations
923
+ - ward
924
+ - ▁audience
925
+ - ird
926
+ - if
927
+ - ▁qu
928
+ - ▁ar
929
+ - ▁definitely
930
+ - ious
931
+ - iting
932
+ - ▁pol
933
+ - ▁huge
934
+ - ▁makes
935
+ - aking
936
+ - ream
937
+ - ance
938
+ - be
939
+ - ▁la
940
+ - ▁ac
941
+ - iter
942
+ - ▁run
943
+ - ▁gotta
944
+ - ▁gr
945
+ - ▁cam
946
+ - sh
947
+ - ▁gets
948
+ - ully
949
+ - ▁says
950
+ - ame
951
+ - side
952
+ - ▁bus
953
+ - ▁shows
954
+ - ▁dr
955
+ - ▁inv
956
+ - ▁idea
957
+ - ▁talking
958
+ - ▁wa
959
+ - way
960
+ - ▁art
961
+ - ▁whatever
962
+ - ▁write
963
+ - ash
964
+ - itt
965
+ - ▁met
966
+ - ▁wants
967
+ - ▁role
968
+ - ▁mu
969
+ - ▁boy
970
+ - ▁wrote
971
+ - ger
972
+ - ately
973
+ - ▁exc
974
+ - ▁mother
975
+ - ▁produ
976
+ - ▁cra
977
+ - ates
978
+ - ▁though
979
+ - av
980
+ - ▁episode
981
+ - ▁sl
982
+ - ▁change
983
+ - ▁voice
984
+ - ▁played
985
+ - ily
986
+ - ▁guess
987
+ - ves
988
+ - ▁hand
989
+ - ady
990
+ - ▁happy
991
+ - ith
992
+ - ▁name
993
+ - ny
994
+ - ▁gi
995
+ - ▁looking
996
+ - lev
997
+ - ▁acting
998
+ - aught
999
+ - iss
1000
+ - ount
1001
+ - rom
1002
+ - ▁tw
1003
+ - ▁cont
1004
+ - ▁john
1005
+ - ▁far
1006
+ - ▁res
1007
+ - ▁sense
1008
+ - ake
1009
+ - ▁basically
1010
+ - ▁meet
1011
+ - ▁gu
1012
+ - ▁bre
1013
+ - ens
1014
+ - cept
1015
+ - ety
1016
+ - ▁girl
1017
+ - ▁york
1018
+ - ▁count
1019
+ - ▁shot
1020
+ - ise
1021
+ - ject
1022
+ - ▁tot
1023
+ - ▁stud
1024
+ - ▁feels
1025
+ - ▁thinking
1026
+ - ▁head
1027
+ - ▁cast
1028
+ - ▁writing
1029
+ - ▁rehe
1030
+ - ▁written
1031
+ - ▁perform
1032
+ - ▁fan
1033
+ - der
1034
+ - ect
1035
+ - ▁sk
1036
+ - ▁hour
1037
+ - ▁father
1038
+ - ered
1039
+ - ▁hundred
1040
+ - ▁ind
1041
+ - ▁norm
1042
+ - ▁acc
1043
+ - up
1044
+ - ▁while
1045
+ - fort
1046
+ - ▁nin
1047
+ - ▁true
1048
+ - itch
1049
+ - ▁inst
1050
+ - ▁second
1051
+ - ▁pick
1052
+ - ▁record
1053
+ - ross
1054
+ - ▁quest
1055
+ - ged
1056
+ - ▁career
1057
+ - ween
1058
+ - ▁bec
1059
+ - ▁reason
1060
+ - ▁since
1061
+ - ▁bra
1062
+ - ▁char
1063
+ - ▁imp
1064
+ - ree
1065
+ - ▁girls
1066
+ - ▁comple
1067
+ - ▁turn
1068
+ - ▁dad
1069
+ - ▁fant
1070
+ - ▁extra
1071
+ - ▁laugh
1072
+ - ▁stand
1073
+ - ▁honest
1074
+ - ▁comm
1075
+ - na
1076
+ - ▁listen
1077
+ - als
1078
+ - cial
1079
+ - spe
1080
+ - ▁ke
1081
+ - ory
1082
+ - view
1083
+ - ink
1084
+ - ▁direct
1085
+ - reat
1086
+ - round
1087
+ - ien
1088
+ - ▁under
1089
+ - ile
1090
+ - ▁diff
1091
+ - ually
1092
+ - ▁tur
1093
+ - thing
1094
+ - sic
1095
+ - ▁gon
1096
+ - ather
1097
+ - ▁aud
1098
+ - ▁scen
1099
+ - atch
1100
+ - ▁sho
1101
+ - ever
1102
+ - tra
1103
+ - ▁pe
1104
+ - mo
1105
+ - ild
1106
+ - ▁care
1107
+ - int
1108
+ - ▁fam
1109
+ - ▁ob
1110
+ - ▁ide
1111
+ - ade
1112
+ - right
1113
+ - ▁may
1114
+ - he
1115
+ - ody
1116
+ - ense
1117
+ - ▁interest
1118
+ - ah
1119
+ - form
1120
+ - ork
1121
+ - ▁episod
1122
+ - ▁rec
1123
+ - iew
1124
+ - ▁hop
1125
+ - ited
1126
+ - ▁exper
1127
+ - gh
1128
+ - ically
1129
+ - ▁bel
1130
+ - ▁el
1131
+ - enty
1132
+ - ▁gott
1133
+ - ▁stu
1134
+ - ▁id
1135
+ - rie
1136
+ - ▁nor
1137
+ - ▁inc
1138
+ - ertain
1139
+ - tain
1140
+ - ▁wo
1141
+ - ▁mon
1142
+ - az
1143
+ - xt
1144
+ - riend
1145
+ - now
1146
+ - ▁list
1147
+ - ime
1148
+ - ome
1149
+ - so
1150
+ - ause
1151
+ - iously
1152
+ - ▁sch
1153
+ - ▁vo
1154
+ - ▁op
1155
+ - ason
1156
+ - ▁mov
1157
+ - ▁hi
1158
+ - ▁pers
1159
+ - ▁ye
1160
+ - ▁def
1161
+ - orm
1162
+ - ▁belie
1163
+ - fore
1164
+ - ix
1165
+ - mber
1166
+ - very
1167
+ - ▁differe
1168
+ - ▁wonder
1169
+ - ek
1170
+ - nder
1171
+ - ▁obv
1172
+ - ▁ep
1173
+ - ship
1174
+ - ▁lau
1175
+ - ience
1176
+ - ool
1177
+ - ▁sin
1178
+ - rect
1179
+ - ▁happ
1180
+ - ▁gir
1181
+ - du
1182
+ - ng
1183
+ - ▁underst
1184
+ - most
1185
+ - eric
1186
+ - ouse
1187
+ - time
1188
+ - lm
1189
+ - ▁hel
1190
+ - redi
1191
+ - ▁cour
1192
+ - ▁relation
1193
+ - rough
1194
+ - q
1195
+ - ▁defin
1196
+ - ▁prob
1197
+ - ▁reme
1198
+ - ▁hu
1199
+ - ▁fir
1200
+ - anna
1201
+ - ways
1202
+ - itten
1203
+ - elt
1204
+ - ▁sometime
1205
+ - ':'
1206
+ - ▁kne
1207
+ - alk
1208
+ - ▁ok
1209
+ - ably
1210
+ - rote
1211
+ - gether
1212
+ - ▁definite
1213
+ - ▁import
1214
+ - '&'
1215
+ - fter
1216
+ - onest
1217
+ - erest
1218
+ - ▁amaz
1219
+ - ▁ano
1220
+ - <sos/eos>
1221
+ transcript_token_list: null
1222
+ two_pass: false
1223
+ pre_postencoder_norm: false
1224
+ init: null
1225
+ input_size: null
1226
+ ctc_conf:
1227
+ dropout_rate: 0.0
1228
+ ctc_type: builtin
1229
+ reduce: true
1230
+ ignore_nan_grad: null
1231
+ zero_infinity: true
1232
+ brctc_risk_strategy: exp
1233
+ brctc_group_strategy: end
1234
+ brctc_risk_factor: 0.0
1235
+ joint_net_conf: null
1236
+ use_preprocessor: true
1237
+ token_type: word
1238
+ bpemodel: null
1239
+ non_linguistic_symbols: null
1240
+ cleaner: null
1241
+ g2p: null
1242
+ speech_volume_normalize: null
1243
+ rir_scp: null
1244
+ rir_apply_prob: 1.0
1245
+ noise_scp: null
1246
+ noise_apply_prob: 1.0
1247
+ noise_db_range: '13_15'
1248
+ short_noise_thres: 0.5
1249
+ frontend: s3prl
1250
+ frontend_conf:
1251
+ frontend_conf:
1252
+ upstream: wavlm_large
1253
+ download_dir: ./hub
1254
+ multilayer_feature: true
1255
+ fs: 16k
1256
+ specaug: specaug
1257
+ specaug_conf:
1258
+ apply_time_warp: true
1259
+ time_warp_window: 5
1260
+ time_warp_mode: bicubic
1261
+ apply_freq_mask: true
1262
+ freq_mask_width_range:
1263
+ - 0
1264
+ - 27
1265
+ num_freq_mask: 2
1266
+ apply_time_mask: true
1267
+ time_mask_width_ratio_range:
1268
+ - 0.0
1269
+ - 0.05
1270
+ num_time_mask: 5
1271
+ normalize: utterance_mvn
1272
+ normalize_conf: {}
1273
+ model: espnet
1274
+ model_conf:
1275
+ ctc_weight: 0.3
1276
+ lsm_weight: 0.1
1277
+ length_normalized_loss: false
1278
+ extract_feats_in_collect_stats: false
1279
+ preencoder: linear
1280
+ preencoder_conf:
1281
+ input_size: 1024
1282
+ output_size: 80
1283
+ encoder: conformer
1284
+ encoder_conf:
1285
+ output_size: 256
1286
+ attention_heads: 4
1287
+ linear_units: 1024
1288
+ num_blocks: 12
1289
+ dropout_rate: 0.1
1290
+ positional_dropout_rate: 0.1
1291
+ attention_dropout_rate: 0.1
1292
+ input_layer: conv2d2
1293
+ normalize_before: true
1294
+ macaron_style: true
1295
+ rel_pos_type: latest
1296
+ pos_enc_layer_type: rel_pos
1297
+ selfattention_layer_type: rel_selfattn
1298
+ activation_type: swish
1299
+ use_cnn_module: true
1300
+ cnn_module_kernel: 31
1301
+ postencoder: null
1302
+ postencoder_conf: {}
1303
+ deliberationencoder: null
1304
+ deliberationencoder_conf: {}
1305
+ decoder: transformer
1306
+ decoder_conf:
1307
+ attention_heads: 4
1308
+ linear_units: 2048
1309
+ num_blocks: 6
1310
+ dropout_rate: 0.1
1311
+ positional_dropout_rate: 0.1
1312
+ self_attention_dropout_rate: 0.1
1313
+ src_attention_dropout_rate: 0.1
1314
+ postdecoder: null
1315
+ postdecoder_conf: {}
1316
+ required:
1317
+ - output_dir
1318
+ - token_list
1319
+ version: '202310'
1320
+ distributed: true
1321
+ ```
1322
+
1323
+ </details>
1324
+
1325
+
1326
+
1327
+ ### Citing ESPnet
1328
+
1329
+ ```BibTex
1330
+ @inproceedings{watanabe2018espnet,
1331
+ author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
1332
+ title={{ESPnet}: End-to-End Speech Processing Toolkit},
1333
+ year={2018},
1334
+ booktitle={Proceedings of Interspeech},
1335
+ pages={2207--2211},
1336
+ doi={10.21437/Interspeech.2018-1456},
1337
+ url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
1338
+ }
1339
+
1340
+
1341
+
1342
+
1343
+
1344
+
1345
+ ```
1346
+
1347
+ or arXiv:
1348
+
1349
+ ```bibtex
1350
+ @misc{watanabe2018espnet,
1351
+ title={ESPnet: End-to-End Speech Processing Toolkit},
1352
+ author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
1353
+ year={2018},
1354
+ eprint={1804.00015},
1355
+ archivePrefix={arXiv},
1356
+ primaryClass={cs.CL}
1357
+ }
1358
+ ```
exp/slu_train_asr_raw_en_word_sp/RESULTS.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!-- Generated by scripts/utils/show_asr_result.sh -->
2
+ # RESULTS
3
+ ## Environments
4
+ - date: `Sun Feb 11 12:27:01 CST 2024`
5
+ - python version: `3.9.13 (main, Aug 25 2022, 23:26:10) [GCC 11.2.0]`
6
+ - espnet version: `espnet 202310`
7
+ - pytorch version: `pytorch 2.1.0+cu121`
8
+ - Git hash: `21d2105784e4da98397bf487b2550d4c6e16d40d`
9
+ - Commit date: `Wed Jan 31 13:40:37 2024 -0600`
10
+
11
+ ## exp/slu_train_asr_raw_en_word_sp
12
+ ### WER
13
+
14
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
15
+ |---|---|---|---|---|---|---|---|---|
16
+ |decode_asr_ctc0.3_beam10_slu_model_valid.acc.ave_10best/test|3530|144908|90.8|6.2|3.0|2.8|12.0|88.9|
17
+ |decode_asr_ctc0.3_slu_model_valid.acc.ave_10best/test|3530|144908|90.1|6.3|3.6|2.9|12.8|89.1|
18
+ |decode_asr_slu_model_valid.acc.ave_10best/devel|1450|58104|91.5|5.5|3.0|2.5|11.0|85.9|
19
+ |decode_asr_slu_model_valid.acc.ave_10best/test|3530|144908|90.1|6.3|3.6|2.9|12.8|89.1|
20
+
21
+ ### CER
22
+
23
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
24
+ |---|---|---|---|---|---|---|---|---|
25
+ |decode_asr_ctc0.3_beam10_slu_model_valid.acc.ave_10best/test|3530|647097|95.6|1.9|2.5|2.6|7.0|88.9|
26
+ |decode_asr_ctc0.3_slu_model_valid.acc.ave_10best/test|3530|647097|95.0|1.9|3.1|2.7|7.7|89.1|
27
+ |decode_asr_slu_model_valid.acc.ave_10best/devel|1450|256305|95.8|1.7|2.5|2.4|6.6|85.9|
28
+ |decode_asr_slu_model_valid.acc.ave_10best/test|3530|647097|95.0|1.9|3.1|2.7|7.7|89.1|
29
+
30
+ ### TER
31
+
32
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
33
+ |---|---|---|---|---|---|---|---|---|
34
+ ## exp/slu_train_asr_raw_en_word_sp/decode_asr_ctc0.3_beam10_slu_model_valid.acc.ave_10best
35
+ ### WER
36
+
37
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
38
+ |---|---|---|---|---|---|---|---|---|
39
+ |org/devel|1451|58267|92.2|5.3|2.5|2.3|10.1|86.0|
40
+
41
+ ### CER
42
+
43
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
44
+ |---|---|---|---|---|---|---|---|---|
45
+ |org/devel|1451|256942|96.4|1.6|2.0|2.2|5.8|86.0|
46
+
47
+ ### TER
48
+
49
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
50
+ |---|---|---|---|---|---|---|---|---|
51
+ ## exp/slu_train_asr_raw_en_word_sp/decode_asr_slu_model_valid.acc.ave_10best
52
+ ### WER
53
+
54
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
55
+ |---|---|---|---|---|---|---|---|---|
56
+ |org/devel|1451|58267|91.5|5.6|3.0|2.6|11.1|85.9|
57
+
58
+ ### CER
59
+
60
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
61
+ |---|---|---|---|---|---|---|---|---|
62
+ |org/devel|1451|256942|95.8|1.7|2.5|2.4|6.6|85.9|
63
+
64
+ ### TER
65
+
66
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
67
+ |---|---|---|---|---|---|---|---|---|
exp/slu_train_asr_raw_en_word_sp/config.yaml ADDED
@@ -0,0 +1,1217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ config: conf/train_asr.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/slu_train_asr_raw_en_word_sp
9
+ ngpu: 1
10
+ seed: 2022
11
+ num_workers: 2
12
+ num_att_plot: 3
13
+ dist_backend: nccl
14
+ dist_init_method: env://
15
+ dist_world_size: 4
16
+ dist_rank: 0
17
+ local_rank: 0
18
+ dist_master_addr: localhost
19
+ dist_master_port: 36647
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: 70
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
+ - acc
41
+ - max
42
+ keep_nbest_models: 10
43
+ nbest_averaging_interval: 10
44
+ grad_clip: 5.0
45
+ grad_clip_type: 2.0
46
+ grad_noise: false
47
+ accum_grad: 1
48
+ no_forward_run: false
49
+ resume: true
50
+ train_dtype: float32
51
+ use_amp: false
52
+ log_interval: 100
53
+ use_matplotlib: true
54
+ use_tensorboard: true
55
+ create_graph_in_tensorboard: false
56
+ use_wandb: false
57
+ wandb_project: null
58
+ wandb_id: null
59
+ wandb_entity: null
60
+ wandb_name: null
61
+ wandb_model_log_interval: -1
62
+ detect_anomaly: false
63
+ use_lora: false
64
+ save_lora_only: true
65
+ lora_conf: {}
66
+ pretrain_path: null
67
+ init_param: []
68
+ ignore_init_mismatch: false
69
+ freeze_param:
70
+ - frontend.upstream
71
+ num_iters_per_epoch: null
72
+ batch_size: 20
73
+ valid_batch_size: null
74
+ batch_bins: 12000000
75
+ valid_batch_bins: null
76
+ train_shape_file:
77
+ - exp/slu_stats_raw_en_word_sp/train/speech_shape
78
+ - exp/slu_stats_raw_en_word_sp/train/text_shape.word
79
+ valid_shape_file:
80
+ - exp/slu_stats_raw_en_word_sp/valid/speech_shape
81
+ - exp/slu_stats_raw_en_word_sp/valid/text_shape.word
82
+ batch_type: numel
83
+ valid_batch_type: null
84
+ fold_length:
85
+ - 80000
86
+ - 150
87
+ sort_in_batch: descending
88
+ shuffle_within_batch: false
89
+ sort_batch: descending
90
+ multiple_iterator: false
91
+ chunk_length: 500
92
+ chunk_shift_ratio: 0.5
93
+ num_cache_chunks: 1024
94
+ chunk_excluded_key_prefixes: []
95
+ chunk_default_fs: null
96
+ train_data_path_and_name_and_type:
97
+ - - dump/raw/train_sp/wav.scp
98
+ - speech
99
+ - sound
100
+ - - dump/raw/train_sp/text
101
+ - text
102
+ - text
103
+ valid_data_path_and_name_and_type:
104
+ - - dump/raw/devel/wav.scp
105
+ - speech
106
+ - sound
107
+ - - dump/raw/devel/text
108
+ - text
109
+ - text
110
+ allow_variable_data_keys: false
111
+ max_cache_size: 0.0
112
+ max_cache_fd: 32
113
+ allow_multi_rates: false
114
+ valid_max_cache_size: null
115
+ exclude_weight_decay: false
116
+ exclude_weight_decay_conf: {}
117
+ optim: adam
118
+ optim_conf:
119
+ lr: 0.002
120
+ weight_decay: 1.0e-06
121
+ scheduler: warmuplr
122
+ scheduler_conf:
123
+ warmup_steps: 5000
124
+ token_list:
125
+ - <blank>
126
+ - <unk>
127
+ - ▁i
128
+ - ▁and
129
+ - ''''
130
+ - s
131
+ - ▁the
132
+ - ▁a
133
+ - ▁it
134
+ - Neutral
135
+ - ▁to
136
+ - ▁you
137
+ - ▁that
138
+ - ▁of
139
+ - ▁in
140
+ - ▁was
141
+ - ▁uh
142
+ - ▁know
143
+ - t
144
+ - ▁so
145
+ - ▁we
146
+ - ▁he
147
+ - ing
148
+ - ▁um
149
+ - ed
150
+ - m
151
+ - ▁like
152
+ - ▁is
153
+ - ▁but
154
+ - Positive
155
+ - y
156
+ - ▁just
157
+ - ▁they
158
+ - re
159
+ - ▁this
160
+ - ▁for
161
+ - ▁be
162
+ - ▁my
163
+ - er
164
+ - ▁with
165
+ - ▁on
166
+ - ▁think
167
+ - ▁p
168
+ - ▁have
169
+ - ▁she
170
+ - e
171
+ - ▁me
172
+ - ▁really
173
+ - ▁there
174
+ - ▁what
175
+ - ▁m
176
+ - a
177
+ - ▁do
178
+ - ▁all
179
+ - i
180
+ - al
181
+ - ve
182
+ - c
183
+ - ▁as
184
+ - ▁about
185
+ - ▁not
186
+ - ▁t
187
+ - n
188
+ - ▁at
189
+ - l
190
+ - ▁had
191
+ - ▁b
192
+ - ▁when
193
+ - ▁c
194
+ - g
195
+ - ar
196
+ - ▁out
197
+ - en
198
+ - ▁s
199
+ - ▁an
200
+ - ▁people
201
+ - or
202
+ - an
203
+ - d
204
+ - o
205
+ - ll
206
+ - ▁are
207
+ - in
208
+ - ▁very
209
+ - p
210
+ - b
211
+ - u
212
+ - ▁because
213
+ - es
214
+ - ▁can
215
+ - ▁don
216
+ - ▁or
217
+ - ▁up
218
+ - it
219
+ - ▁one
220
+ - ly
221
+ - ▁if
222
+ - ▁f
223
+ - st
224
+ - ▁were
225
+ - ▁mean
226
+ - ▁d
227
+ - ▁who
228
+ - ▁then
229
+ - ic
230
+ - 'on'
231
+ - ▁no
232
+ - ▁go
233
+ - ▁her
234
+ - ▁g
235
+ - ent
236
+ - ▁st
237
+ - ▁kind
238
+ - ri
239
+ - ▁would
240
+ - ▁get
241
+ - ▁e
242
+ - le
243
+ - at
244
+ - r
245
+ - ▁time
246
+ - ▁w
247
+ - ▁re
248
+ - h
249
+ - ▁from
250
+ - ▁l
251
+ - ▁said
252
+ - ▁him
253
+ - ▁how
254
+ - v
255
+ - ▁well
256
+ - ▁h
257
+ - ▁gonna
258
+ - ▁lot
259
+ - ▁see
260
+ - f
261
+ - ▁his
262
+ - et
263
+ - ion
264
+ - ▁been
265
+ - ▁great
266
+ - ▁yeah
267
+ - ▁love
268
+ - ▁which
269
+ - ▁got
270
+ - k
271
+ - ▁them
272
+ - ▁way
273
+ - id
274
+ - ▁show
275
+ - w
276
+ - ▁some
277
+ - ▁your
278
+ - ▁did
279
+ - ▁sort
280
+ - ▁has
281
+ - ▁things
282
+ - ▁back
283
+ - ▁where
284
+ - ▁something
285
+ - ir
286
+ - ▁thing
287
+ - ad
288
+ - ▁su
289
+ - ▁ch
290
+ - ▁n
291
+ - il
292
+ - as
293
+ - ▁j
294
+ - ▁more
295
+ - se
296
+ - ▁say
297
+ - ▁co
298
+ - nd
299
+ - ▁much
300
+ - ▁always
301
+ - ine
302
+ - ▁r
303
+ - ation
304
+ - ur
305
+ - ▁other
306
+ - th
307
+ - ▁
308
+ - ▁se
309
+ - ▁now
310
+ - ate
311
+ - ▁doing
312
+ - ▁work
313
+ - ow
314
+ - ▁could
315
+ - ally
316
+ - ▁these
317
+ - Negative
318
+ - ▁good
319
+ - ▁any
320
+ - ers
321
+ - ce
322
+ - ▁cause
323
+ - ▁ex
324
+ - ▁pro
325
+ - ▁little
326
+ - ▁actually
327
+ - ▁into
328
+ - ▁make
329
+ - ▁first
330
+ - ▁being
331
+ - ra
332
+ - ▁our
333
+ - ▁al
334
+ - ▁by
335
+ - ▁film
336
+ - ▁didn
337
+ - ▁v
338
+ - ct
339
+ - ity
340
+ - ch
341
+ - un
342
+ - ▁part
343
+ - ▁de
344
+ - ▁come
345
+ - is
346
+ - ie
347
+ - ▁right
348
+ - ▁o
349
+ - ▁off
350
+ - ol
351
+ - ▁two
352
+ - ▁never
353
+ - ▁le
354
+ - ot
355
+ - ut
356
+ - ▁movie
357
+ - ▁play
358
+ - ge
359
+ - ies
360
+ - el
361
+ - ▁con
362
+ - am
363
+ - ▁going
364
+ - ke
365
+ - ▁want
366
+ - im
367
+ - ▁feel
368
+ - ive
369
+ - ro
370
+ - ▁mo
371
+ - ▁different
372
+ - ck
373
+ - ▁life
374
+ - ist
375
+ - ▁oh
376
+ - all
377
+ - ▁lo
378
+ - ard
379
+ - ▁went
380
+ - and
381
+ - ▁sh
382
+ - ▁even
383
+ - ry
384
+ - ▁years
385
+ - ▁look
386
+ - ▁us
387
+ - ant
388
+ - ▁te
389
+ - ▁k
390
+ - ▁li
391
+ - ▁happen
392
+ - ure
393
+ - ▁their
394
+ - ▁those
395
+ - ▁take
396
+ - ment
397
+ - ▁day
398
+ - ble
399
+ - ast
400
+ - ▁every
401
+ - um
402
+ - ill
403
+ - op
404
+ - ▁thought
405
+ - ou
406
+ - us
407
+ - ay
408
+ - ▁th
409
+ - ▁put
410
+ - ▁story
411
+ - ▁new
412
+ - ▁down
413
+ - ish
414
+ - ▁big
415
+ - ▁wanna
416
+ - ▁ro
417
+ - ▁also
418
+ - ▁read
419
+ - ▁around
420
+ - ous
421
+ - ▁through
422
+ - red
423
+ - ▁came
424
+ - ▁character
425
+ - ess
426
+ - te
427
+ - ver
428
+ - ▁will
429
+ - ag
430
+ - ss
431
+ - ▁fun
432
+ - ▁over
433
+ - ▁many
434
+ - ▁bl
435
+ - ▁cl
436
+ - ▁man
437
+ - ▁than
438
+ - ▁pre
439
+ - ▁world
440
+ - ▁person
441
+ - z
442
+ - ▁sp
443
+ - ven
444
+ - ▁wanted
445
+ - ▁bit
446
+ - ▁before
447
+ - ▁mar
448
+ - one
449
+ - ab
450
+ - ▁en
451
+ - ci
452
+ - ▁set
453
+ - ▁ha
454
+ - ▁find
455
+ - ul
456
+ - ▁fi
457
+ - ▁end
458
+ - ▁un
459
+ - ▁sc
460
+ - ▁after
461
+ - ind
462
+ - ter
463
+ - ▁working
464
+ - ▁why
465
+ - om
466
+ - me
467
+ - ▁such
468
+ - ▁whole
469
+ - ▁kinda
470
+ - ne
471
+ - ▁bo
472
+ - x
473
+ - ▁most
474
+ - ▁ad
475
+ - ▁guy
476
+ - ▁spe
477
+ - ars
478
+ - ▁am
479
+ - ful
480
+ - ▁together
481
+ - ▁let
482
+ - ▁quite
483
+ - ain
484
+ - ▁everything
485
+ - ▁made
486
+ - ig
487
+ - ▁old
488
+ - able
489
+ - ▁tr
490
+ - ak
491
+ - ▁fo
492
+ - ▁po
493
+ - ore
494
+ - ice
495
+ - ▁real
496
+ - ▁knew
497
+ - ▁hard
498
+ - pp
499
+ - age
500
+ - ated
501
+ - ▁same
502
+ - ▁start
503
+ - ▁ever
504
+ - ning
505
+ - ▁watch
506
+ - art
507
+ - ▁again
508
+ - ▁here
509
+ - are
510
+ - ght
511
+ - ong
512
+ - ▁done
513
+ - ▁only
514
+ - ▁live
515
+ - ▁wasn
516
+ - ▁ho
517
+ - ▁u
518
+ - ▁maybe
519
+ - ▁need
520
+ - ▁everybody
521
+ - ust
522
+ - ans
523
+ - ▁three
524
+ - ▁having
525
+ - ▁music
526
+ - ack
527
+ - ld
528
+ - ▁trying
529
+ - ▁guys
530
+ - rou
531
+ - ach
532
+ - ving
533
+ - ▁tell
534
+ - ▁should
535
+ - ff
536
+ - ide
537
+ - ▁four
538
+ - ▁started
539
+ - ▁com
540
+ - ass
541
+ - ▁long
542
+ - ▁fe
543
+ - ▁course
544
+ - ▁called
545
+ - ▁own
546
+ - ress
547
+ - ▁moment
548
+ - ▁pl
549
+ - ▁still
550
+ - ▁anything
551
+ - ▁family
552
+ - ▁fin
553
+ - ▁dan
554
+ - ▁bro
555
+ - 'no'
556
+ - ther
557
+ - ▁per
558
+ - ▁amazing
559
+ - ▁stuff
560
+ - per
561
+ - ▁jo
562
+ - ▁certain
563
+ - os
564
+ - ▁talk
565
+ - ater
566
+ - ▁help
567
+ - ▁too
568
+ - ▁year
569
+ - ight
570
+ - ▁fa
571
+ - self
572
+ - ces
573
+ - ▁br
574
+ - ▁bet
575
+ - ▁someone
576
+ - ▁di
577
+ - ▁sing
578
+ - nt
579
+ - ick
580
+ - ▁ph
581
+ - row
582
+ - ▁script
583
+ - ▁remember
584
+ - ▁try
585
+ - qu
586
+ - ite
587
+ - ▁young
588
+ - ▁wh
589
+ - ▁ser
590
+ - ▁ask
591
+ - ▁book
592
+ - ▁each
593
+ - ▁wr
594
+ - ▁best
595
+ - ▁ag
596
+ - ▁women
597
+ - ose
598
+ - ions
599
+ - ved
600
+ - j
601
+ - ue
602
+ - ▁does
603
+ - ▁five
604
+ - ▁both
605
+ - ▁friends
606
+ - ▁act
607
+ - iz
608
+ - cess
609
+ - pt
610
+ - ▁somebody
611
+ - ft
612
+ - ▁nice
613
+ - ▁myself
614
+ - een
615
+ - fe
616
+ - sp
617
+ - ict
618
+ - ty
619
+ - ▁child
620
+ - ud
621
+ - pe
622
+ - ▁hope
623
+ - ▁fact
624
+ - ▁saying
625
+ - ave
626
+ - icul
627
+ - au
628
+ - ale
629
+ - ris
630
+ - ▁twenty
631
+ - ▁school
632
+ - ▁doesn
633
+ - ▁able
634
+ - pect
635
+ - ▁last
636
+ - ber
637
+ - ▁song
638
+ - od
639
+ - ▁str
640
+ - ▁interesting
641
+ - lf
642
+ - ▁em
643
+ - ▁wor
644
+ - ap
645
+ - og
646
+ - ▁ra
647
+ - ▁dis
648
+ - ▁coming
649
+ - ▁ab
650
+ - ▁house
651
+ - ▁next
652
+ - ▁tra
653
+ - ▁okay
654
+ - ere
655
+ - ary
656
+ - ▁incredi
657
+ - ▁car
658
+ - ▁job
659
+ - ▁used
660
+ - ▁give
661
+ - ▁god
662
+ - ▁americ
663
+ - ▁characters
664
+ - ▁app
665
+ - ▁walk
666
+ - ▁yes
667
+ - rew
668
+ - ▁getting
669
+ - ▁six
670
+ - ▁chan
671
+ - ▁ne
672
+ - ▁pretty
673
+ - ang
674
+ - ▁creat
675
+ - ▁another
676
+ - ▁ter
677
+ - ▁kids
678
+ - ▁felt
679
+ - ▁sometimes
680
+ - ▁place
681
+ - out
682
+ - ▁funny
683
+ - ase
684
+ - ich
685
+ - act
686
+ - ▁days
687
+ - ▁hum
688
+ - ▁bring
689
+ - ts
690
+ - ▁making
691
+ - ▁comp
692
+ - ▁become
693
+ - ute
694
+ - ▁wonderful
695
+ - ron
696
+ - les
697
+ - ▁saw
698
+ - ▁point
699
+ - ia
700
+ - ▁realiz
701
+ - ▁int
702
+ - ▁away
703
+ - ays
704
+ - ▁home
705
+ - ace
706
+ - ▁relationship
707
+ - ▁woman
708
+ - ▁everyone
709
+ - ▁comes
710
+ - ▁high
711
+ - dd
712
+ - ▁night
713
+ - ath
714
+ - ▁else
715
+ - vent
716
+ - ▁shoot
717
+ - vers
718
+ - day
719
+ - ▁sure
720
+ - ried
721
+ - ned
722
+ - ▁obviously
723
+ - ▁dra
724
+ - ▁inter
725
+ - co
726
+ - ▁playing
727
+ - ▁important
728
+ - ort
729
+ - uck
730
+ - ision
731
+ - pport
732
+ - ▁seen
733
+ - pl
734
+ - ▁fl
735
+ - ound
736
+ - ▁bas
737
+ - ull
738
+ - est
739
+ - ▁actor
740
+ - ▁lear
741
+ - ▁worked
742
+ - ▁believe
743
+ - ▁gen
744
+ - ▁keep
745
+ - ▁friend
746
+ - ▁sw
747
+ - ▁des
748
+ - ▁times
749
+ - ▁im
750
+ - ▁sur
751
+ - ▁sit
752
+ - ▁probably
753
+ - ok
754
+ - ▁took
755
+ - ep
756
+ - ough
757
+ - ip
758
+ - ood
759
+ - ▁sa
760
+ - ▁season
761
+ - vel
762
+ - wn
763
+ - ▁dec
764
+ - ▁excited
765
+ - ian
766
+ - ire
767
+ - ph
768
+ - ▁month
769
+ - ner
770
+ - ▁min
771
+ - ▁rel
772
+ - ating
773
+ - body
774
+ - ition
775
+ - ▁loved
776
+ - ▁aw
777
+ - ▁hear
778
+ - ple
779
+ - ▁cool
780
+ - ▁y
781
+ - ord
782
+ - our
783
+ - ▁game
784
+ - ms
785
+ - ub
786
+ - ▁might
787
+ - ▁kid
788
+ - ▁movies
789
+ - ical
790
+ - ▁bad
791
+ - ▁scene
792
+ - iv
793
+ - ▁enough
794
+ - ▁sm
795
+ - bly
796
+ - ▁fift
797
+ - ▁eight
798
+ - ▁experience
799
+ - ▁actors
800
+ - ▁cou
801
+ - ▁understand
802
+ - ▁week
803
+ - ▁few
804
+ - gin
805
+ - ting
806
+ - ▁director
807
+ - ▁almost
808
+ - ▁open
809
+ - ren
810
+ - ▁star
811
+ - ▁room
812
+ - ▁call
813
+ - oy
814
+ - ▁goes
815
+ - ▁told
816
+ - ▁once
817
+ - ▁found
818
+ - arly
819
+ - ations
820
+ - ward
821
+ - ▁audience
822
+ - ird
823
+ - if
824
+ - ▁qu
825
+ - ▁ar
826
+ - ▁definitely
827
+ - ious
828
+ - iting
829
+ - ▁pol
830
+ - ▁huge
831
+ - ▁makes
832
+ - aking
833
+ - ream
834
+ - ance
835
+ - be
836
+ - ▁la
837
+ - ▁ac
838
+ - iter
839
+ - ▁run
840
+ - ▁gotta
841
+ - ▁gr
842
+ - ▁cam
843
+ - sh
844
+ - ▁gets
845
+ - ully
846
+ - ▁says
847
+ - ame
848
+ - side
849
+ - ▁bus
850
+ - ▁shows
851
+ - ▁dr
852
+ - ▁inv
853
+ - ▁idea
854
+ - ▁talking
855
+ - ▁wa
856
+ - way
857
+ - ▁art
858
+ - ▁whatever
859
+ - ▁write
860
+ - ash
861
+ - itt
862
+ - ▁met
863
+ - ▁wants
864
+ - ▁role
865
+ - ▁mu
866
+ - ▁boy
867
+ - ▁wrote
868
+ - ger
869
+ - ately
870
+ - ▁exc
871
+ - ▁mother
872
+ - ▁produ
873
+ - ▁cra
874
+ - ates
875
+ - ▁though
876
+ - av
877
+ - ▁episode
878
+ - ▁sl
879
+ - ▁change
880
+ - ▁voice
881
+ - ▁played
882
+ - ily
883
+ - ▁guess
884
+ - ves
885
+ - ▁hand
886
+ - ady
887
+ - ▁happy
888
+ - ith
889
+ - ▁name
890
+ - ny
891
+ - ▁gi
892
+ - ▁looking
893
+ - lev
894
+ - ▁acting
895
+ - aught
896
+ - iss
897
+ - ount
898
+ - rom
899
+ - ▁tw
900
+ - ▁cont
901
+ - ▁john
902
+ - ▁far
903
+ - ▁res
904
+ - ▁sense
905
+ - ake
906
+ - ▁basically
907
+ - ▁meet
908
+ - ▁gu
909
+ - ▁bre
910
+ - ens
911
+ - cept
912
+ - ety
913
+ - ▁girl
914
+ - ▁york
915
+ - ▁count
916
+ - ▁shot
917
+ - ise
918
+ - ject
919
+ - ▁tot
920
+ - ▁stud
921
+ - ▁feels
922
+ - ▁thinking
923
+ - ▁head
924
+ - ▁cast
925
+ - ▁writing
926
+ - ▁rehe
927
+ - ▁written
928
+ - ▁perform
929
+ - ▁fan
930
+ - der
931
+ - ect
932
+ - ▁sk
933
+ - ▁hour
934
+ - ▁father
935
+ - ered
936
+ - ▁hundred
937
+ - ▁ind
938
+ - ▁norm
939
+ - ▁acc
940
+ - up
941
+ - ▁while
942
+ - fort
943
+ - ▁nin
944
+ - ▁true
945
+ - itch
946
+ - ▁inst
947
+ - ▁second
948
+ - ▁pick
949
+ - ▁record
950
+ - ross
951
+ - ▁quest
952
+ - ged
953
+ - ▁career
954
+ - ween
955
+ - ▁bec
956
+ - ▁reason
957
+ - ▁since
958
+ - ▁bra
959
+ - ▁char
960
+ - ▁imp
961
+ - ree
962
+ - ▁girls
963
+ - ▁comple
964
+ - ▁turn
965
+ - ▁dad
966
+ - ▁fant
967
+ - ▁extra
968
+ - ▁laugh
969
+ - ▁stand
970
+ - ▁honest
971
+ - ▁comm
972
+ - na
973
+ - ▁listen
974
+ - als
975
+ - cial
976
+ - spe
977
+ - ▁ke
978
+ - ory
979
+ - view
980
+ - ink
981
+ - ▁direct
982
+ - reat
983
+ - round
984
+ - ien
985
+ - ▁under
986
+ - ile
987
+ - ▁diff
988
+ - ually
989
+ - ▁tur
990
+ - thing
991
+ - sic
992
+ - ▁gon
993
+ - ather
994
+ - ▁aud
995
+ - ▁scen
996
+ - atch
997
+ - ▁sho
998
+ - ever
999
+ - tra
1000
+ - ▁pe
1001
+ - mo
1002
+ - ild
1003
+ - ▁care
1004
+ - int
1005
+ - ▁fam
1006
+ - ▁ob
1007
+ - ▁ide
1008
+ - ade
1009
+ - right
1010
+ - ▁may
1011
+ - he
1012
+ - ody
1013
+ - ense
1014
+ - ▁interest
1015
+ - ah
1016
+ - form
1017
+ - ork
1018
+ - ▁episod
1019
+ - ▁rec
1020
+ - iew
1021
+ - ▁hop
1022
+ - ited
1023
+ - ▁exper
1024
+ - gh
1025
+ - ically
1026
+ - ▁bel
1027
+ - ▁el
1028
+ - enty
1029
+ - ▁gott
1030
+ - ▁stu
1031
+ - ▁id
1032
+ - rie
1033
+ - ▁nor
1034
+ - ▁inc
1035
+ - ertain
1036
+ - tain
1037
+ - ▁wo
1038
+ - ▁mon
1039
+ - az
1040
+ - xt
1041
+ - riend
1042
+ - now
1043
+ - ▁list
1044
+ - ime
1045
+ - ome
1046
+ - so
1047
+ - ause
1048
+ - iously
1049
+ - ▁sch
1050
+ - ▁vo
1051
+ - ▁op
1052
+ - ason
1053
+ - ▁mov
1054
+ - ▁hi
1055
+ - ▁pers
1056
+ - ▁ye
1057
+ - ▁def
1058
+ - orm
1059
+ - ▁belie
1060
+ - fore
1061
+ - ix
1062
+ - mber
1063
+ - very
1064
+ - ▁differe
1065
+ - ▁wonder
1066
+ - ek
1067
+ - nder
1068
+ - ▁obv
1069
+ - ▁ep
1070
+ - ship
1071
+ - ▁lau
1072
+ - ience
1073
+ - ool
1074
+ - ▁sin
1075
+ - rect
1076
+ - ▁happ
1077
+ - ▁gir
1078
+ - du
1079
+ - ng
1080
+ - ▁underst
1081
+ - most
1082
+ - eric
1083
+ - ouse
1084
+ - time
1085
+ - lm
1086
+ - ▁hel
1087
+ - redi
1088
+ - ▁cour
1089
+ - ▁relation
1090
+ - rough
1091
+ - q
1092
+ - ▁defin
1093
+ - ▁prob
1094
+ - ▁reme
1095
+ - ▁hu
1096
+ - ▁fir
1097
+ - anna
1098
+ - ways
1099
+ - itten
1100
+ - elt
1101
+ - ▁sometime
1102
+ - ':'
1103
+ - ▁kne
1104
+ - alk
1105
+ - ▁ok
1106
+ - ably
1107
+ - rote
1108
+ - gether
1109
+ - ▁definite
1110
+ - ▁import
1111
+ - '&'
1112
+ - fter
1113
+ - onest
1114
+ - erest
1115
+ - ▁amaz
1116
+ - ▁ano
1117
+ - <sos/eos>
1118
+ transcript_token_list: null
1119
+ two_pass: false
1120
+ pre_postencoder_norm: false
1121
+ init: null
1122
+ input_size: null
1123
+ ctc_conf:
1124
+ dropout_rate: 0.0
1125
+ ctc_type: builtin
1126
+ reduce: true
1127
+ ignore_nan_grad: null
1128
+ zero_infinity: true
1129
+ brctc_risk_strategy: exp
1130
+ brctc_group_strategy: end
1131
+ brctc_risk_factor: 0.0
1132
+ joint_net_conf: null
1133
+ use_preprocessor: true
1134
+ token_type: word
1135
+ bpemodel: null
1136
+ non_linguistic_symbols: null
1137
+ cleaner: null
1138
+ g2p: null
1139
+ speech_volume_normalize: null
1140
+ rir_scp: null
1141
+ rir_apply_prob: 1.0
1142
+ noise_scp: null
1143
+ noise_apply_prob: 1.0
1144
+ noise_db_range: '13_15'
1145
+ short_noise_thres: 0.5
1146
+ frontend: s3prl
1147
+ frontend_conf:
1148
+ frontend_conf:
1149
+ upstream: wavlm_large
1150
+ download_dir: ./hub
1151
+ multilayer_feature: true
1152
+ fs: 16k
1153
+ specaug: specaug
1154
+ specaug_conf:
1155
+ apply_time_warp: true
1156
+ time_warp_window: 5
1157
+ time_warp_mode: bicubic
1158
+ apply_freq_mask: true
1159
+ freq_mask_width_range:
1160
+ - 0
1161
+ - 27
1162
+ num_freq_mask: 2
1163
+ apply_time_mask: true
1164
+ time_mask_width_ratio_range:
1165
+ - 0.0
1166
+ - 0.05
1167
+ num_time_mask: 5
1168
+ normalize: utterance_mvn
1169
+ normalize_conf: {}
1170
+ model: espnet
1171
+ model_conf:
1172
+ ctc_weight: 0.3
1173
+ lsm_weight: 0.1
1174
+ length_normalized_loss: false
1175
+ extract_feats_in_collect_stats: false
1176
+ preencoder: linear
1177
+ preencoder_conf:
1178
+ input_size: 1024
1179
+ output_size: 80
1180
+ encoder: conformer
1181
+ encoder_conf:
1182
+ output_size: 256
1183
+ attention_heads: 4
1184
+ linear_units: 1024
1185
+ num_blocks: 12
1186
+ dropout_rate: 0.1
1187
+ positional_dropout_rate: 0.1
1188
+ attention_dropout_rate: 0.1
1189
+ input_layer: conv2d2
1190
+ normalize_before: true
1191
+ macaron_style: true
1192
+ rel_pos_type: latest
1193
+ pos_enc_layer_type: rel_pos
1194
+ selfattention_layer_type: rel_selfattn
1195
+ activation_type: swish
1196
+ use_cnn_module: true
1197
+ cnn_module_kernel: 31
1198
+ postencoder: null
1199
+ postencoder_conf: {}
1200
+ deliberationencoder: null
1201
+ deliberationencoder_conf: {}
1202
+ decoder: transformer
1203
+ decoder_conf:
1204
+ attention_heads: 4
1205
+ linear_units: 2048
1206
+ num_blocks: 6
1207
+ dropout_rate: 0.1
1208
+ positional_dropout_rate: 0.1
1209
+ self_attention_dropout_rate: 0.1
1210
+ src_attention_dropout_rate: 0.1
1211
+ postdecoder: null
1212
+ postdecoder_conf: {}
1213
+ required:
1214
+ - output_dir
1215
+ - token_list
1216
+ version: '202310'
1217
+ distributed: true
exp/slu_train_asr_raw_en_word_sp/images/acc.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/backward_time.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/cer.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/cer_ctc.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/clip.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/forward_time.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/gpu_max_cached_mem_GB.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/grad_norm.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/iter_time.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/loss.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/loss_att.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/loss_ctc.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/loss_scale.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/optim0_lr0.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/optim_step_time.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/train_time.png ADDED
exp/slu_train_asr_raw_en_word_sp/images/wer.png ADDED
exp/slu_train_asr_raw_en_word_sp/valid.acc.ave_10best.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640eb1d7bf775b9d9c6cf4628be27fc1e3d38ee5eb7ba0914bb7650e21125064
3
+ size 1391920902
meta.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ espnet: '202310'
2
+ files:
3
+ slu_model_file: exp/slu_train_asr_raw_en_word_sp/valid.acc.ave_10best.pth
4
+ python: "3.9.13 (main, Aug 25 2022, 23:26:10) \n[GCC 11.2.0]"
5
+ timestamp: 1715356573.373284
6
+ torch: 2.1.0+cu121
7
+ yaml_files:
8
+ slu_train_config: exp/slu_train_asr_raw_en_word_sp/config.yaml