“siddhu001”
commited on
Commit
·
6916e78
1
Parent(s):
0f2f29d
Add Task Specifier model
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- add_tokens-Copy1.txt +460 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/RESULTS.md +65 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/config.yaml +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_0.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_1.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_10.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_11.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_12.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_13.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_14.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_15.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_16.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_2.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_3.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_4.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_5.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_6.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_7.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_8.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_9.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/backward_time.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_0.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_1.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_10.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_11.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_12.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_13.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_14.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_15.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_16.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_2.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_3.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_4.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_5.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_6.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_7.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_8.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_9.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/forward_time.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/gpu_max_cached_mem_GB.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/iter_time.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_0.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_1.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_10.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_11.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_12.png +0 -0
- exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_13.png +0 -0
add_tokens-Copy1.txt
ADDED
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
command:yes
|
2 |
+
command:down
|
3 |
+
command:no
|
4 |
+
command:stop
|
5 |
+
command:go
|
6 |
+
command:on
|
7 |
+
command:left
|
8 |
+
command:right
|
9 |
+
command:_unknown_
|
10 |
+
command:_silence_
|
11 |
+
command:off
|
12 |
+
command:up
|
13 |
+
em:neu
|
14 |
+
em:ang
|
15 |
+
em:sad
|
16 |
+
em:hap
|
17 |
+
em:oth
|
18 |
+
in:increase_heat_washroom
|
19 |
+
in:deactivate_lights_none
|
20 |
+
in:deactivate_lights_bedroom
|
21 |
+
in:decrease_heat_none
|
22 |
+
in:deactivate_lights_kitchen
|
23 |
+
in:change_language_none_none
|
24 |
+
in:activate_music_none
|
25 |
+
in:change_language_English_none
|
26 |
+
in:activate_lights_none
|
27 |
+
in:deactivate_lights_washroom
|
28 |
+
in:change_language_German_none
|
29 |
+
in:decrease_heat_kitchen
|
30 |
+
in:increase_volume_none
|
31 |
+
in:decrease_heat_bedroom
|
32 |
+
in:deactivate_music_none
|
33 |
+
in:decrease_volume_none
|
34 |
+
in:change_language_Chinese_none
|
35 |
+
in:decrease_heat_washroom
|
36 |
+
in:change_language_Korean_none
|
37 |
+
in:increase_heat_none
|
38 |
+
in:bring_newspaper_none
|
39 |
+
in:activate_lamp_none
|
40 |
+
in:deactivate_lamp_none
|
41 |
+
in:bring_juice_none
|
42 |
+
in:activate_lights_kitchen
|
43 |
+
in:increase_heat_kitchen
|
44 |
+
in:bring_socks_none
|
45 |
+
in:activate_lights_bedroom
|
46 |
+
in:increase_heat_bedroom
|
47 |
+
in:activate_lights_washroom
|
48 |
+
in:bring_shoes_none
|
49 |
+
command:A
|
50 |
+
command:B
|
51 |
+
command:C
|
52 |
+
command:D
|
53 |
+
command:E
|
54 |
+
command:F
|
55 |
+
command:0
|
56 |
+
command:1
|
57 |
+
command:2
|
58 |
+
command:3
|
59 |
+
command:4
|
60 |
+
command:5
|
61 |
+
command:6
|
62 |
+
command:7
|
63 |
+
command:8
|
64 |
+
command:9
|
65 |
+
accent:american
|
66 |
+
accent:australian
|
67 |
+
accent:bangla
|
68 |
+
accent:british
|
69 |
+
accent:indian
|
70 |
+
accent:malayalam
|
71 |
+
accent:odiya
|
72 |
+
accent:telugu
|
73 |
+
accent:welsh
|
74 |
+
class:spoof
|
75 |
+
class:bonafide
|
76 |
+
lang:ru
|
77 |
+
lang:es
|
78 |
+
lang:it
|
79 |
+
lang:en
|
80 |
+
lang:fr
|
81 |
+
lang:de
|
82 |
+
class:sarcasm
|
83 |
+
class:not_sarcasm
|
84 |
+
gender:f
|
85 |
+
gender:m
|
86 |
+
audio_class:43
|
87 |
+
audio_class:1
|
88 |
+
audio_class:10
|
89 |
+
audio_class:17
|
90 |
+
audio_class:37
|
91 |
+
audio_class:35
|
92 |
+
audio_class:29
|
93 |
+
audio_class:11
|
94 |
+
audio_class:3
|
95 |
+
audio_class:19
|
96 |
+
audio_class:32
|
97 |
+
audio_class:16
|
98 |
+
audio_class:47
|
99 |
+
audio_class:44
|
100 |
+
audio_class:13
|
101 |
+
audio_class:36
|
102 |
+
audio_class:39
|
103 |
+
audio_class:20
|
104 |
+
audio_class:24
|
105 |
+
audio_class:14
|
106 |
+
audio_class:9
|
107 |
+
audio_class:26
|
108 |
+
audio_class:5
|
109 |
+
audio_class:28
|
110 |
+
audio_class:8
|
111 |
+
audio_class:30
|
112 |
+
audio_class:0
|
113 |
+
audio_class:48
|
114 |
+
audio_class:21
|
115 |
+
audio_class:31
|
116 |
+
audio_class:38
|
117 |
+
audio_class:6
|
118 |
+
audio_class:45
|
119 |
+
audio_class:33
|
120 |
+
audio_class:15
|
121 |
+
audio_class:34
|
122 |
+
audio_class:2
|
123 |
+
audio_class:7
|
124 |
+
audio_class:49
|
125 |
+
audio_class:12
|
126 |
+
audio_class:40
|
127 |
+
audio_class:25
|
128 |
+
audio_class:22
|
129 |
+
audio_class:4
|
130 |
+
audio_class:42
|
131 |
+
audio_class:41
|
132 |
+
audio_class:23
|
133 |
+
audio_class:46
|
134 |
+
audio_class:18
|
135 |
+
audio_class:27
|
136 |
+
vad_class:speech
|
137 |
+
<|audio|>
|
138 |
+
<|ic|>
|
139 |
+
<|scr|>
|
140 |
+
<|er|>
|
141 |
+
<|accent_rec|>
|
142 |
+
<|fsd|>
|
143 |
+
<|lid|>
|
144 |
+
<|scd|>
|
145 |
+
<|gid|>
|
146 |
+
<|auc|>
|
147 |
+
<|vad|>
|
148 |
+
<|google_scr|>
|
149 |
+
<|grabo_scr|>
|
150 |
+
<|lt_scr|>
|
151 |
+
<|ar_scr|>
|
152 |
+
<|fsc|>
|
153 |
+
<|voxforge|>
|
154 |
+
<|asvspoof|>
|
155 |
+
<|iemocap|>
|
156 |
+
<|accentdb|>
|
157 |
+
<|mustard|>
|
158 |
+
<|mustard_plus_plus|>
|
159 |
+
<|voxceleb|>
|
160 |
+
<|esc50|>
|
161 |
+
<|freesound|>
|
162 |
+
in:increasebrightness
|
163 |
+
in:setlightcolor
|
164 |
+
in:setlightbrightness
|
165 |
+
in:switchlighton
|
166 |
+
in:decreasebrightness
|
167 |
+
in:switchlightoff
|
168 |
+
in:music_likeness
|
169 |
+
in:music_settings
|
170 |
+
in:play_music
|
171 |
+
in:iot_hue_lightoff
|
172 |
+
in:play_radio
|
173 |
+
in:weather_query
|
174 |
+
in:cooking_recipe
|
175 |
+
in:email_sendemail
|
176 |
+
in:calendar_set
|
177 |
+
in:lists_remove
|
178 |
+
in:play_podcasts
|
179 |
+
in:qa_definition
|
180 |
+
in:audio_volume_up
|
181 |
+
in:news_query
|
182 |
+
in:general_quirky
|
183 |
+
in:email_query
|
184 |
+
in:audio_volume_down
|
185 |
+
in:takeaway_query
|
186 |
+
in:general_joke
|
187 |
+
in:iot_hue_lightup
|
188 |
+
in:takeaway_order
|
189 |
+
in:audio_volume_mute
|
190 |
+
in:iot_hue_lightdim
|
191 |
+
in:calendar_query
|
192 |
+
in:transport_query
|
193 |
+
in:transport_taxi
|
194 |
+
in:general_greet
|
195 |
+
in:music_query
|
196 |
+
in:iot_coffee
|
197 |
+
in:qa_maths
|
198 |
+
in:email_querycontact
|
199 |
+
in:recommendation_movies
|
200 |
+
in:alarm_remove
|
201 |
+
in:calendar_remove
|
202 |
+
in:datetime_query
|
203 |
+
in:iot_hue_lightchange
|
204 |
+
in:iot_wemo_off
|
205 |
+
in:transport_ticket
|
206 |
+
in:alarm_query
|
207 |
+
in:transport_traffic
|
208 |
+
in:recommendation_events
|
209 |
+
in:lists_createoradd
|
210 |
+
in:social_query
|
211 |
+
in:social_post
|
212 |
+
in:qa_stock
|
213 |
+
in:lists_query
|
214 |
+
in:qa_factoid
|
215 |
+
in:recommendation_locations
|
216 |
+
in:audio_volume_other
|
217 |
+
in:qa_currency
|
218 |
+
in:iot_cleaning
|
219 |
+
in:play_audiobook
|
220 |
+
in:alarm_set
|
221 |
+
in:datetime_convert
|
222 |
+
in:play_game
|
223 |
+
in:iot_wemo_on
|
224 |
+
in:music_dislikeness
|
225 |
+
in:email_addcontact
|
226 |
+
in:iot_hue_lighton
|
227 |
+
in:cooking_query
|
228 |
+
in:qa_query
|
229 |
+
in:general_negate
|
230 |
+
in:general_dontcare
|
231 |
+
in:general_repeat
|
232 |
+
in:general_affirm
|
233 |
+
in:general_commandstop
|
234 |
+
in:general_confirm
|
235 |
+
in:general_explain
|
236 |
+
in:general_praise
|
237 |
+
sl:player_setting
|
238 |
+
sl:song_name
|
239 |
+
sl:house_place
|
240 |
+
sl:timeofday
|
241 |
+
sl:weather_descriptor
|
242 |
+
sl:device_type
|
243 |
+
sl:relation
|
244 |
+
sl:event_name
|
245 |
+
sl:general_frequency
|
246 |
+
sl:definition_word
|
247 |
+
sl:date
|
248 |
+
sl:time
|
249 |
+
sl:person
|
250 |
+
sl:food_type
|
251 |
+
sl:order_type
|
252 |
+
sl:business_type
|
253 |
+
sl:change_amount
|
254 |
+
sl:place_name
|
255 |
+
sl:transport_type
|
256 |
+
sl:personal_info
|
257 |
+
sl:radio_name
|
258 |
+
sl:ingredient
|
259 |
+
sl:music_genre
|
260 |
+
sl:artist_name
|
261 |
+
sl:music_descriptor
|
262 |
+
sl:playlist_name
|
263 |
+
sl:news_topic
|
264 |
+
sl:color_type
|
265 |
+
sl:podcast_descriptor
|
266 |
+
sl:list_name
|
267 |
+
sl:media_type
|
268 |
+
sl:transport_name
|
269 |
+
sl:cooking_type
|
270 |
+
sl:joke_type
|
271 |
+
sl:currency_name
|
272 |
+
sl:email_folder
|
273 |
+
sl:app_name
|
274 |
+
sl:audiobook_name
|
275 |
+
sl:business_name
|
276 |
+
sl:meal_type
|
277 |
+
sl:podcast_name
|
278 |
+
sl:drink_type
|
279 |
+
sl:game_name
|
280 |
+
sl:transport_agency
|
281 |
+
sl:sport_type
|
282 |
+
sl:movie_name
|
283 |
+
sl:email_address
|
284 |
+
sl:transport_descriptor
|
285 |
+
sl:alarm_type
|
286 |
+
sl:coffee_type
|
287 |
+
sl:movie_type
|
288 |
+
sl:audiobook_author
|
289 |
+
sl:game_type
|
290 |
+
sl:music_album
|
291 |
+
sl:query_detail
|
292 |
+
SEP
|
293 |
+
FILL
|
294 |
+
in:create_alarm_STOP
|
295 |
+
sl:date_time_STOP
|
296 |
+
in:get_alarm_STOP
|
297 |
+
in:unsupported_alarm_STOP
|
298 |
+
in:delete_alarm_STOP
|
299 |
+
sl:alarm_name_STOP
|
300 |
+
in:get_time_STOP
|
301 |
+
sl:date_time_recurring_STOP
|
302 |
+
sl:amount_STOP
|
303 |
+
sl:duration_STOP
|
304 |
+
in:silence_alarm_STOP
|
305 |
+
sl:ordinal_STOP
|
306 |
+
in:snooze_alarm_STOP
|
307 |
+
in:update_alarm_STOP
|
308 |
+
sl:period_STOP
|
309 |
+
sl:time_zone_STOP
|
310 |
+
sl:recurring_date_time_STOP
|
311 |
+
in:get_event_STOP
|
312 |
+
sl:location_STOP
|
313 |
+
in:get_location_STOP
|
314 |
+
sl:point_on_map_STOP
|
315 |
+
sl:category_event_STOP
|
316 |
+
sl:search_radius_STOP
|
317 |
+
sl:location_user_STOP
|
318 |
+
sl:attribute_event_STOP
|
319 |
+
in:get_event_attendee_STOP
|
320 |
+
sl:attendee_event_STOP
|
321 |
+
sl:location_modifier_STOP
|
322 |
+
sl:category_location_STOP
|
323 |
+
sl:name_event_STOP
|
324 |
+
in:unsupported_event_STOP
|
325 |
+
in:get_location_home_STOP
|
326 |
+
sl:contact_STOP
|
327 |
+
in:get_location_school_STOP
|
328 |
+
in:get_contact_STOP
|
329 |
+
sl:contact_related_STOP
|
330 |
+
sl:type_relation_STOP
|
331 |
+
sl:organizer_event_STOP
|
332 |
+
in:get_location_work_STOP
|
333 |
+
in:negation_STOP
|
334 |
+
in:get_event_organizer_STOP
|
335 |
+
in:get_event_attendee_amount_STOP
|
336 |
+
in:get_message_STOP
|
337 |
+
in:send_message_STOP
|
338 |
+
sl:recipient_STOP
|
339 |
+
sl:content_exact_STOP
|
340 |
+
in:react_message_STOP
|
341 |
+
sl:type_reaction_STOP
|
342 |
+
sl:type_content_STOP
|
343 |
+
in:cancel_message_STOP
|
344 |
+
sl:group_STOP
|
345 |
+
sl:location_home_STOP
|
346 |
+
sl:content_emoji_STOP
|
347 |
+
sl:type_contact_STOP
|
348 |
+
sl:sender_STOP
|
349 |
+
sl:mutual_employer_STOP
|
350 |
+
sl:resource_STOP
|
351 |
+
sl:mutual_school_STOP
|
352 |
+
sl:type_info_STOP
|
353 |
+
sl:mutual_location_STOP
|
354 |
+
sl:tag_message_STOP
|
355 |
+
in:unsupported_messaging_STOP
|
356 |
+
in:ignore_message_STOP
|
357 |
+
in:send_text_message_STOP
|
358 |
+
sl:age_STOP
|
359 |
+
in:loop_music_STOP
|
360 |
+
sl:music_type_STOP
|
361 |
+
in:replay_music_STOP
|
362 |
+
in:previous_track_music_STOP
|
363 |
+
sl:music_track_title_STOP
|
364 |
+
in:pause_music_STOP
|
365 |
+
sl:music_playlist_title_STOP
|
366 |
+
sl:music_provider_name_STOP
|
367 |
+
in:skip_track_music_STOP
|
368 |
+
sl:music_artist_name_STOP
|
369 |
+
in:start_shuffle_music_STOP
|
370 |
+
in:dislike_music_STOP
|
371 |
+
in:remove_from_playlist_music_STOP
|
372 |
+
in:like_music_STOP
|
373 |
+
sl:music_album_title_STOP
|
374 |
+
in:create_playlist_music_STOP
|
375 |
+
in:stop_music_STOP
|
376 |
+
in:unsupported_music_STOP
|
377 |
+
in:add_to_playlist_music_STOP
|
378 |
+
sl:music_radio_id_STOP
|
379 |
+
in:get_estimated_duration_STOP
|
380 |
+
sl:method_travel_STOP
|
381 |
+
sl:source_STOP
|
382 |
+
sl:destination_STOP
|
383 |
+
in:unsupported_navigation_STOP
|
384 |
+
in:get_estimated_arrival_STOP
|
385 |
+
sl:date_time_arrival_STOP
|
386 |
+
sl:date_time_departure_STOP
|
387 |
+
in:get_estimated_departure_STOP
|
388 |
+
in:get_info_traffic_STOP
|
389 |
+
in:get_directions_STOP
|
390 |
+
sl:path_STOP
|
391 |
+
in:get_info_road_condition_STOP
|
392 |
+
sl:road_condition_STOP
|
393 |
+
in:get_distance_STOP
|
394 |
+
sl:unit_distance_STOP
|
395 |
+
in:update_directions_STOP
|
396 |
+
sl:obstruction_avoid_STOP
|
397 |
+
sl:path_avoid_STOP
|
398 |
+
in:get_info_route_STOP
|
399 |
+
sl:road_condition_avoid_STOP
|
400 |
+
sl:waypoint_STOP
|
401 |
+
sl:location_work_STOP
|
402 |
+
sl:waypoint_avoid_STOP
|
403 |
+
sl:location_current_STOP
|
404 |
+
in:get_location_hometown_STOP
|
405 |
+
sl:waypoint_added_STOP
|
406 |
+
in:create_reminder_STOP
|
407 |
+
sl:person_reminded_STOP
|
408 |
+
sl:todo_STOP
|
409 |
+
in:get_recurring_date_time_STOP
|
410 |
+
sl:frequency_STOP
|
411 |
+
in:delete_reminder_STOP
|
412 |
+
in:get_todo_STOP
|
413 |
+
in:update_reminder_STOP
|
414 |
+
in:update_reminder_todo_STOP
|
415 |
+
sl:todo_new_STOP
|
416 |
+
in:update_reminder_date_time_STOP
|
417 |
+
sl:date_time_new_STOP
|
418 |
+
in:get_reminder_STOP
|
419 |
+
sl:attendee_STOP
|
420 |
+
in:reply_message_STOP
|
421 |
+
sl:method_retrieval_reminder_STOP
|
422 |
+
sl:recurring_date_time_new_STOP
|
423 |
+
sl:person_reminded_added_STOP
|
424 |
+
in:get_reminder_date_time_STOP
|
425 |
+
sl:person_reminded_removed_STOP
|
426 |
+
in:get_reminder_location_STOP
|
427 |
+
in:get_reminder_amount_STOP
|
428 |
+
in:help_reminder_STOP
|
429 |
+
sl:name_app_STOP
|
430 |
+
sl:attendee_removed_STOP
|
431 |
+
sl:attendee_added_STOP
|
432 |
+
sl:job_STOP
|
433 |
+
in:get_birthday_STOP
|
434 |
+
in:create_timer_STOP
|
435 |
+
sl:method_timer_STOP
|
436 |
+
in:pause_timer_STOP
|
437 |
+
in:get_timer_STOP
|
438 |
+
in:add_time_timer_STOP
|
439 |
+
sl:timer_name_STOP
|
440 |
+
in:restart_timer_STOP
|
441 |
+
in:subtract_time_timer_STOP
|
442 |
+
in:delete_timer_STOP
|
443 |
+
in:resume_timer_STOP
|
444 |
+
in:unsupported_timer_STOP
|
445 |
+
in:update_timer_STOP
|
446 |
+
in:get_weather_STOP
|
447 |
+
sl:weather_attribute_STOP
|
448 |
+
in:get_sunset_STOP
|
449 |
+
in:unsupported_weather_STOP
|
450 |
+
in:get_sunrise_STOP
|
451 |
+
sl:weather_temperature_unit_STOP
|
452 |
+
sl:measurement_unit_STOP
|
453 |
+
in:get_info_contact_STOP
|
454 |
+
in:play_music_STOP
|
455 |
+
sl:music_genre_STOP
|
456 |
+
<|ner|>
|
457 |
+
<|sp|>
|
458 |
+
<|STOP|>
|
459 |
+
<|SLURP|>
|
460 |
+
<|SNIPS|>
|
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/RESULTS.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<!-- Generated by scripts/utils/show_asr_result.sh -->
|
2 |
+
# RESULTS
|
3 |
+
## Environments
|
4 |
+
- date: `Sun Jul 16 11:29:20 CDT 2023`
|
5 |
+
- python version: `3.9.13 (main, Aug 25 2022, 23:26:10) [GCC 11.2.0]`
|
6 |
+
- espnet version: `espnet 202211`
|
7 |
+
- pytorch version: `pytorch 1.12.1+cu116`
|
8 |
+
- Git hash: `69261333fd675bacaf981ec33505aec180bfbb38`
|
9 |
+
- Commit date: `Tue Nov 30 16:12:53 2021 -0500`
|
10 |
+
|
11 |
+
## asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual
|
12 |
+
### WER
|
13 |
+
|
14 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
15 |
+
|---|---|---|---|---|---|---|---|---|
|
16 |
+
|decode_asr_accent_rec_asr_model_valid.acc.ave/test_accentdb|3463|3463|99.9|0.1|0.0|0.0|0.1|0.1|
|
17 |
+
|decode_asr_ar_asr_model_valid.acc.ave/test_arabic|370|370|100.0|0.0|0.0|0.0|0.0|0.0|
|
18 |
+
|decode_asr_auc_asr_model_valid.acc.ave/test_esc50|400|400|67.3|32.8|0.0|0.3|33.0|32.8|
|
19 |
+
|decode_asr_er_asr_model_valid.acc.ave/test_iemocap|942|11962|91.0|6.4|2.6|2.5|11.5|63.1|
|
20 |
+
|decode_asr_fsd_asr_model_valid.acc.ave/test_asvspoof|71237|71237|98.0|2.0|0.0|0.0|2.0|2.0|
|
21 |
+
|decode_asr_gid_asr_model_valid.acc.ave/test_voxceleb|4818|4818|99.9|0.1|0.0|0.0|0.1|0.1|
|
22 |
+
|decode_asr_grabo_asr_model_valid.acc.ave/test_grabo|3631|3631|99.7|0.3|0.0|0.0|0.3|0.3|
|
23 |
+
|decode_asr_ic1_asr_model_valid.acc.ave/test_snips|166|1470|95.2|2.2|2.6|1.9|6.7|30.1|
|
24 |
+
|decode_asr_ic_asr_model_valid.acc.ave/test_fsc|3793|20316|99.8|0.1|0.1|0.1|0.2|0.7|
|
25 |
+
|decode_asr_ic_asr_model_valid.acc.ave/test_snips|166|1470|0.0|0.0|100.0|0.0|100.0|100.0|
|
26 |
+
|decode_asr_lid_asr_model_valid.acc.ave/test_voxforge|1800|1800|99.9|0.1|0.0|0.0|0.1|0.1|
|
27 |
+
|decode_asr_lt_asr_model_valid.acc.ave/test_lt_speech_commands|88|88|98.9|1.1|0.0|0.0|1.1|1.1|
|
28 |
+
|decode_asr_ner1_1_asr_model_valid.acc.ave/test_slurp|13078|164549|90.7|4.8|4.5|3.2|12.5|41.7|
|
29 |
+
|decode_asr_scd_asr_model_valid.acc.ave/test_mustard|138|138|73.9|26.1|0.0|0.0|26.1|26.1|
|
30 |
+
|decode_asr_scd_plus_asr_model_valid.acc.ave/test_mustard_plus_plus|92|92|70.7|29.3|0.0|0.0|29.3|29.3|
|
31 |
+
|decode_asr_scr_asr_model_valid.acc.ave/test_speechcommands|4890|4890|99.1|0.9|0.0|0.0|0.9|0.9|
|
32 |
+
|decode_asr_sp2_asr_model_valid.acc.ave/test|75636|728701|94.9|1.8|3.3|2.2|7.3|21.6|
|
33 |
+
|old_decode_asr_auc_asr_model_valid.acc.ave/test_esc50|400|400|63.0|37.0|0.0|0.0|37.0|37.0|
|
34 |
+
|old_decode_asr_scd_asr_model_valid.acc.ave/test_mustard|138|138|73.9|26.1|0.0|0.0|26.1|26.1|
|
35 |
+
|old_decode_asr_scd_plus_asr_model_valid.acc.ave/test_mustard_plus_plus|92|92|73.9|26.1|0.0|0.0|26.1|26.1|
|
36 |
+
|
37 |
+
### CER
|
38 |
+
|
39 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
40 |
+
|---|---|---|---|---|---|---|---|---|
|
41 |
+
|decode_asr_accent_rec_asr_model_valid.acc.ave/test_accentdb|3463|25897|100.0|0.0|0.0|0.0|0.1|0.1|
|
42 |
+
|decode_asr_ar_asr_model_valid.acc.ave/test_arabic|370|370|100.0|0.0|0.0|0.0|0.0|0.0|
|
43 |
+
|decode_asr_auc_asr_model_valid.acc.ave/test_esc50|400|528|41.3|48.9|9.8|23.7|82.4|61.0|
|
44 |
+
|decode_asr_er_asr_model_valid.acc.ave/test_iemocap|942|58253|95.5|2.1|2.4|2.5|7.0|63.1|
|
45 |
+
|decode_asr_fsd_asr_model_valid.acc.ave/test_asvspoof|71237|378250|98.9|0.7|0.4|1.5|2.6|2.0|
|
46 |
+
|decode_asr_gid_asr_model_valid.acc.ave/test_voxceleb|4818|4818|99.9|0.1|0.0|0.0|0.1|0.1|
|
47 |
+
|decode_asr_grabo_asr_model_valid.acc.ave/test_grabo|3631|168247|99.9|0.0|0.0|0.0|0.1|0.3|
|
48 |
+
|decode_asr_ic1_asr_model_valid.acc.ave/test_snips|166|6533|96.4|0.7|2.9|2.3|5.9|30.1|
|
49 |
+
|decode_asr_ic_asr_model_valid.acc.ave/test_fsc|3793|172445|99.9|0.0|0.1|0.0|0.1|0.7|
|
50 |
+
|decode_asr_ic_asr_model_valid.acc.ave/test_snips|166|6533|0.0|0.0|100.0|0.0|100.0|100.0|
|
51 |
+
|decode_asr_lid_asr_model_valid.acc.ave/test_voxforge|1800|3600|99.9|0.1|0.0|0.0|0.1|0.1|
|
52 |
+
|decode_asr_lt_asr_model_valid.acc.ave/test_lt_speech_commands|88|526|98.9|0.4|0.8|0.0|1.1|1.1|
|
53 |
+
|decode_asr_ner1_1_asr_model_valid.acc.ave/test_slurp|13078|669743|93.5|1.8|4.7|3.2|9.7|41.8|
|
54 |
+
|decode_asr_scd_asr_model_valid.acc.ave/test_mustard|138|138|73.9|26.1|0.0|0.0|26.1|26.1|
|
55 |
+
|decode_asr_scd_plus_asr_model_valid.acc.ave/test_mustard_plus_plus|92|92|70.7|29.3|0.0|0.0|29.3|29.3|
|
56 |
+
|decode_asr_scr_asr_model_valid.acc.ave/test_speechcommands|4890|19959|99.2|0.4|0.4|0.4|1.2|0.9|
|
57 |
+
|decode_asr_sp2_asr_model_valid.acc.ave/test|75636|5377833|95.9|0.6|3.5|2.2|6.4|21.6|
|
58 |
+
|old_decode_asr_auc_asr_model_valid.acc.ave/test_esc50|400|544|38.2|43.4|18.4|6.6|68.4|58.3|
|
59 |
+
|old_decode_asr_scd_asr_model_valid.acc.ave/test_mustard|138|138|73.9|26.1|0.0|0.0|26.1|26.1|
|
60 |
+
|old_decode_asr_scd_plus_asr_model_valid.acc.ave/test_mustard_plus_plus|92|92|73.9|26.1|0.0|0.0|26.1|26.1|
|
61 |
+
|
62 |
+
### TER
|
63 |
+
|
64 |
+
|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
|
65 |
+
|---|---|---|---|---|---|---|---|---|
|
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/config.yaml
ADDED
The diff for this file is too large to render.
See raw diff
|
|
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_0.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_1.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_10.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_11.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_12.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_13.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_14.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_15.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_16.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_2.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_3.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_4.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_5.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_6.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_7.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_8.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/acc_9.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/backward_time.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_0.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_1.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_10.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_11.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_12.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_13.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_14.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_15.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_16.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_2.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_3.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_4.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_5.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_6.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_7.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_8.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/cer_9.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/forward_time.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/gpu_max_cached_mem_GB.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/iter_time.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_0.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_1.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_10.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_11.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_12.png
ADDED
![]() |
exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/images/loss_13.png
ADDED
![]() |