DRAFT
Soudscapes via AudioGen
|
|
|
|---|---|
|
See level classhing on the iceberg of lighhouse |
|
|
Loug scene of restaurant in medieval city |
|
|
Nikolskoe bei der Wasser an der Havel in Berlin-Zehlendorf, nahe der Pfaueninsel. Beliebtes Berliner Ausflugsziel |
Draft after this line
Following examples are the Harvard sentences synthesized via StyleTTS2 - using Mimic-3 or accelerated 4x speed Mimic-3 styles or Librispeech segments
Trial 3
New Tablo - tts_harvard.py =======================================================
|
Prompt - ( |
StyleTTS2 - (First 20 Harvard Sentences) |
|---|---|
|
Mimic-3 English |
StyleTTS - (Mimic-3 English) From Above |
|
Mimic-3 English 4x |
StyleTTS2 - (Mimic-3 English 4x) |
|
Human |
StyleTTS2 - (Human) |
|
Mimic-3 Foreign |
StyleTTS2 - (Mimic-3 Foreign) |
|
Mimix-3 Foreign 4x |
StyleTTS2 - (Mimic-3 Foreign 4x) |
Please edit for MOS annotation
|
|
|
|
0 |
1 |
|
2 |
3 |
|
4 5 |
6 7 |
|
8 |
9 |
|
10 |
11 |
4 4
1 4
5 5
5 4
3 4
1 4
2 3
1 4
5 4
5 4
2 3
1 2
A B
4* 5
3* 5
5 5
5 4
2 5
1 4
*ignoring the breath-noise between sentences
DEBUG Multi-sentence Foreign Langs
|
Language & Call |
TxT |
|---|---|
|
δέομαι ὑμῶν, ὦ ἄνδρες Ἀθηναῖοι, ἐθελῆσαί μου μετ᾽ εὐνοίας ἀκοῦσαι λέγοντος, ὑπολογιζομένους τό τε μέγεθος τοῦ κινδύνου καὶ τὸ πλῆθος τῶν αἰτιῶν πρὸς ἂς ἀπολογήσασθαί με δεῖ, καὶ τὰς τέχνας καὶ τὰς κατασκευὰς τοῦ κατηγόρου καὶ τὴν ὠμότητα, ὃς ἐτόλμησε παρακελεύσασθαι |
Native English Voices TTS
Diffusion steps = 7 / artficially generated styles how mimic3 english 4x speed - python
Non native English TTS
# first start Flask api.py
python tts.py --text a.txt --voice "af_ZA_google-nwu_0184"
| voice | TTS | |
|---|---|---|
|
0 |
af_ZA_google-nwu_0184 |
|
|
1 |
af_ZA_google-nwu_1919 |
|
|
2 |
af_ZA_google-nwu_2418 |
|
|
3 |
af_ZA_google-nwu_6590 |
|
|
4 |
af_ZA_google-nwu_7130 |
|
|
5 |
af_ZA_google-nwu_7214 |
|
|
6 |
af_ZA_google-nwu_8148 |
|
|
7 |
af_ZA_google-nwu_8924 |
|
|
8 |
af_ZA_google-nwu_8963 |
|
|
9 |
bn_multi_00737 |
|
|
10 |
bn_multi_00779 |
|
|
11 |
bn_multi_01232 |
|
|
12 |
bn_multi_01701 |
|
|
13 |
bn_multi_03042 |
|
|
14 |
bn_multi_0834 |
|
|
15 |
bn_multi_1010 |
|
|
16 |
bn_multi_3108 |
|
|
17 |
bn_multi_3713 |
|
|
18 |
bn_multi_3958 |
|
|
19 |
bn_multi_4046 |
|
|
20 |
bn_multi_4811 |
|
|
21 |
bn_multi_5958 |
|
|
22 |
bn_multi_9169 |
|
|
23 |
bn_multi_rm |
|
|
24 |
de_DE_m-ailabs_angela_merkel |
|
|
25 |
de_DE_m-ailabs_eva_k |
|
|
26 |
de_DE_m-ailabs_karlsson |
|
|
27 |
de_DE_m-ailabs_ramona_deininger |
|
|
28 |
de_DE_m-ailabs_rebecca_braunert_plunkett |
|
|
29 |
de_DE_thorsten-emotion_amused |
|
|
30 |
de_DE_thorsten-emotion_angry |
|
|
31 |
de_DE_thorsten-emotion_disgusted |
|
|
32 |
de_DE_thorsten-emotion_drunk |
|
|
33 |
de_DE_thorsten-emotion_neutral |
|
|
34 |
de_DE_thorsten-emotion_sleepy |
|
|
35 |
de_DE_thorsten-emotion_surprised |
|
|
36 |
de_DE_thorsten-emotion_whisper |
|
|
37 |
de_DE_thorsten |
|
|
38 |
el_GR_rapunzelina |
|
|
39 |
es_ES_carlfm |
|
|
40 |
es_ES_m-ailabs_karen_savage |
|
|
41 |
es_ES_m-ailabs_tux |
|
|
42 |
es_ES_m-ailabs_victor_villarraza |
|
|
43 |
fa_haaniye |
|
|
44 |
fi_FI_harri-tapani-ylilammi |
|
|
45 |
fr_FR_m-ailabs_bernard |
|
|
46 |
fr_FR_m-ailabs_ezwa |
|
|
47 |
fr_FR_m-ailabs_gilles_g_le_blanc |
|
|
48 |
fr_FR_m-ailabs_nadine_eckert_boulet |
|
|
49 |
fr_FR_m-ailabs_zeckou |
|
|
50 |
fr_FR_siwis |
|
|
51 |
fr_FR_tom |
|
|
52 |
gu_IN_cmu-indic_cmu_indic_guj_ad |
|
|
53 |
gu_IN_cmu-indic_cmu_indic_guj_dp |
|
|
54 |
gu_IN_cmu-indic_cmu_indic_guj_kt |
|
|
55 |
ha_NE_openbible |
|
|
56 |
hu_HU_diana-majlinger |
|
|
57 |
it_IT_mls_10446 |
|
|
58 |
it_IT_mls_1157 |
|
|
59 |
it_IT_mls_12428 |
|
|
60 |
it_IT_mls_12804 |
|
|
61 |
it_IT_mls_1595 |
|
|
62 |
it_IT_mls_1725 |
|
|
63 |
it_IT_mls_1989 |
|
|
64 |
it_IT_mls_2019 |
|
|
65 |
it_IT_mls_2033 |
|
|
66 |
it_IT_mls_277 |
|
|
67 |
it_IT_mls_4649 |
|
|
68 |
it_IT_mls_4705 |
|
|
69 |
it_IT_mls_4971 |
|
|
70 |
it_IT_mls_4974 |
|
|
71 |
it_IT_mls_4975 |
|
|
72 |
it_IT_mls_4998 |
|
|
73 |
it_IT_mls_5010 |
|
|
74 |
it_IT_mls_5421 |
|
|
75 |
it_IT_mls_6001 |
|
|
76 |
it_IT_mls_6299 |
|
|
77 |
it_IT_mls_6348 |
|
|
78 |
it_IT_mls_643 |
|
|
79 |
it_IT_mls_644 |
|
|
80 |
it_IT_mls_659 |
|
|
81 |
it_IT_mls_6744 |
|
|
82 |
it_IT_mls_6807 |
|
|
83 |
it_IT_mls_7405 |
|
|
84 |
it_IT_mls_7440 |
|
|
85 |
it_IT_mls_7444 |
|
|
86 |
it_IT_mls_7936 |
|
|
87 |
it_IT_mls_8181 |
|
|
88 |
it_IT_mls_8207 |
|
|
89 |
it_IT_mls_8384 |
|
|
90 |
it_IT_mls_844 |
|
|
91 |
it_IT_mls_8461 |
|
|
92 |
it_IT_mls_8828 |
|
|
93 |
it_IT_mls_8842 |
|
|
94 |
it_IT_mls_9185 |
|
|
95 |
it_IT_mls_9772 |
|
|
96 |
it_IT_riccardo-fasol |
|
|
97 |
jv_ID_google-gmu_00027 |
|
|
98 |
jv_ID_google-gmu_00264 |
|
|
99 |
jv_ID_google-gmu_00658 |
|
|
100 |
jv_ID_google-gmu_01392 |
|
|
101 |
jv_ID_google-gmu_01519 |
|
|
102 |
jv_ID_google-gmu_01932 |
|
|
103 |
jv_ID_google-gmu_02059 |
|
|
104 |
jv_ID_google-gmu_02326 |
|
|
105 |
jv_ID_google-gmu_02884 |
|
|
106 |
jv_ID_google-gmu_03187 |
|
|
107 |
jv_ID_google-gmu_03314 |
|
|
108 |
jv_ID_google-gmu_03424 |
|
|
109 |
jv_ID_google-gmu_03727 |
|
|
110 |
jv_ID_google-gmu_04175 |
|
|
111 |
jv_ID_google-gmu_04285 |
|
|
112 |
jv_ID_google-gmu_04588 |
|
|
113 |
jv_ID_google-gmu_04679 |
|
|
114 |
jv_ID_google-gmu_04715 |
|
|
115 |
jv_ID_google-gmu_04982 |
|
|
116 |
jv_ID_google-gmu_05219 |
|
|
117 |
jv_ID_google-gmu_05522 |
|
|
118 |
jv_ID_google-gmu_05540 |
|
|
119 |
jv_ID_google-gmu_05667 |
|
|
120 |
jv_ID_google-gmu_05970 |
|
|
121 |
jv_ID_google-gmu_06080 |
|
|
122 |
jv_ID_google-gmu_06207 |
|
|
123 |
jv_ID_google-gmu_06383 |
|
|
124 |
jv_ID_google-gmu_06510 |
|
|
125 |
jv_ID_google-gmu_06941 |
|
|
126 |
jv_ID_google-gmu_07335 |
|
|
127 |
jv_ID_google-gmu_07638 |
|
|
128 |
jv_ID_google-gmu_07765 |
|
|
129 |
jv_ID_google-gmu_07875 |
|
|
130 |
jv_ID_google-gmu_08002 |
|
|
131 |
jv_ID_google-gmu_08178 |
|
|
132 |
jv_ID_google-gmu_08305 |
|
|
133 |
jv_ID_google-gmu_08736 |
|
|
134 |
jv_ID_google-gmu_09039 |
|
|
135 |
jv_ID_google-gmu_09724 |
|
|
136 |
ko_KO_kss |
|
|
137 |
ne_NP_ne-google_0258 |
|
|
138 |
ne_NP_ne-google_0283 |
|
|
139 |
ne_NP_ne-google_0546 |
|
|
140 |
ne_NP_ne-google_0649 |
|
|
141 |
ne_NP_ne-google_0883 |
|
|
142 |
ne_NP_ne-google_2027 |
|
|
143 |
ne_NP_ne-google_2099 |
|
|
144 |
ne_NP_ne-google_2139 |
|
|
145 |
ne_NP_ne-google_3154 |
|
|
146 |
ne_NP_ne-google_3614 |
|
|
147 |
ne_NP_ne-google_3960 |
|
|
148 |
ne_NP_ne-google_3997 |
|
|
149 |
ne_NP_ne-google_5687 |
|
|
150 |
ne_NP_ne-google_6329 |
|
|
151 |
ne_NP_ne-google_6587 |
|
|
152 |
ne_NP_ne-google_6834 |
|
|
153 |
ne_NP_ne-google_7957 |
|
|
154 |
ne_NP_ne-google_9407 |
|
|
155 |
nl_bart-de-leeuw |
|
|
156 |
nl_flemishguy |
|
|
157 |
nl_nathalie |
|
|
158 |
nl_pmk |
|
|
159 |
nl_rdh |
|
|
160 |
pl_PL_m-ailabs_nina_brown |
|
|
161 |
pl_PL_m-ailabs_piotr_nater |
|
|
162 |
ru_RU_multi_hajdurova |
|
|
163 |
ru_RU_multi_minaev |
|
|
164 |
ru_RU_multi_nikolaev |
|
|
165 |
sw_lanfrica |
|
|
166 |
te_IN_cmu-indic_kpn |
|
|
167 |
te_IN_cmu-indic_sk |
|
|
168 |
te_IN_cmu-indic_ss |
|
|
169 |
tn_ZA_google-nwu_0045 |
|
|
170 |
tn_ZA_google-nwu_0378 |
|
|
171 |
tn_ZA_google-nwu_0441 |
|
|
172 |
tn_ZA_google-nwu_1483 |
|
|
173 |
tn_ZA_google-nwu_1498 |
|
|
174 |
tn_ZA_google-nwu_1932 |
|
|
175 |
tn_ZA_google-nwu_2839 |
|
|
176 |
tn_ZA_google-nwu_3342 |
|
|
177 |
tn_ZA_google-nwu_3629 |
|
|
178 |
tn_ZA_google-nwu_4506 |
|
|
179 |
tn_ZA_google-nwu_4850 |
|
|
180 |
tn_ZA_google-nwu_5628 |
|
|
181 |
tn_ZA_google-nwu_6116 |
|
|
182 |
tn_ZA_google-nwu_6206 |
|
|
183 |
tn_ZA_google-nwu_6234 |
|
|
184 |
tn_ZA_google-nwu_6459 |
|
|
185 |
tn_ZA_google-nwu_7674 |
|
|
186 |
tn_ZA_google-nwu_7693 |
|
|
187 |
tn_ZA_google-nwu_7866 |
|
|
188 |
tn_ZA_google-nwu_7896 |
|
|
189 |
tn_ZA_google-nwu_8333 |
|
|
190 |
tn_ZA_google-nwu_8512 |
|
|
191 |
tn_ZA_google-nwu_8532 |
|
|
192 |
tn_ZA_google-nwu_8914 |
|
|
193 |
tn_ZA_google-nwu_9061 |
|
|
194 |
tn_ZA_google-nwu_9365 |
|
|
195 |
vi_VN_vais1000 |
|
|
196 |
yo_openbible |
|
Native English Voices
- A voice is defined by a 2s artificial audio - generated by mimic3 TTS - then given to StyleTTS2 as speaker
# first start Flask api.py
python tts.py --text a.txt --voice " en_US_cmu_arctic_aew"
| voice | TTS | |
|---|---|---|
|
0 |
en_US_cmu_arctic_aew |
|
|
1 |
en_US_cmu_arctic_ahw |
|
|
2 |
en_US_cmu_arctic_aup |
|
|
3 |
en_US_cmu_arctic_awbrms |
|
|
4 |
en_US_cmu_arctic_axb |
|
|
5 |
en_US_cmu_arctic_bdl |
|
|
6 |
en_US_cmu_arctic_clb |
|
|
7 |
en_US_cmu_arctic_eey |
|
|
8 |
en_US_cmu_arctic_fem |
|
|
9 |
en_US_cmu_arctic_gka |
|
|
10 |
en_US_cmu_arctic_jmk |
|
|
11 |
en_US_cmu_arctic_ksp |
|
|
12 |
en_US_cmu_arctic_ljm |
|
|
13 |
en_US_cmu_arctic_lnh |
|
|
14 |
en_US_cmu_arctic_rxr |
|
|
15 |
en_US_cmu_arctic_slp |
|
|
16 |
en_US_cmu_arctic_slt |
|
|
17 |
en_US_hifi-tts_6097 |
|
|
18 |
en_US_hifi-tts_9017 |
|
|
19 |
en_US_hifi-tts_92 |
|
|
20 |
en_US_ljspeech |
|
|
21 |
en_US_m-ailabs_elliot_miller |
|
|
22 |
en_US_m-ailabs_judy_bieber |
|
|
23 |
en_US_m-ailabs_mary_ann |
|
|
24 |
en_US_vctk_p225 |
|
|
25 |
en_US_vctk_p226 |
|
|
26 |
en_US_vctk_p227 |
|
|
27 |
en_US_vctk_p228 |
|
|
28 |
en_US_vctk_p229 |
|
|
29 |
en_US_vctk_p230 |
|
|
30 |
en_US_vctk_p231 |
|
|
31 |
en_US_vctk_p232 |
|
|
32 |
en_US_vctk_p233 |
|
|
33 |
en_US_vctk_p234 |
|
|
34 |
en_US_vctk_p236 |
|
|
35 |
en_US_vctk_p237 |
|
|
36 |
en_US_vctk_p238 |
|
|
37 |
en_US_vctk_p239 |
|
|
38 |
en_US_vctk_p240 |
|
|
39 |
en_US_vctk_p241 |
|
|
40 |
en_US_vctk_p243 |
|
|
41 |
en_US_vctk_p244 |
|
|
42 |
en_US_vctk_p245 |
|
|
43 |
en_US_vctk_p246 |
|
|
44 |
en_US_vctk_p247 |
|
|
45 |
en_US_vctk_p248 |
|
|
46 |
en_US_vctk_p249 |
|
|
47 |
en_US_vctk_p250 |
|
|
48 |
en_US_vctk_p251 |
|
|
49 |
en_US_vctk_p252 |
|
|
50 |
en_US_vctk_p253 |
|
|
51 |
en_US_vctk_p254 |
|
|
52 |
en_US_vctk_p255 |
|
|
53 |
en_US_vctk_p256 |
|
|
54 |
en_US_vctk_p257 |
|
|
55 |
en_US_vctk_p258 |
|
|
56 |
en_US_vctk_p259 |
|
|
57 |
en_US_vctk_p260 |
|
|
58 |
en_US_vctk_p261 |
|
|
59 |
en_US_vctk_p262 |
|
|
60 |
en_US_vctk_p263 |
|
|
61 |
en_US_vctk_p264 |
|
|
62 |
en_US_vctk_p265 |
|
|
63 |
en_US_vctk_p266 |
|
|
64 |
en_US_vctk_p267 |
|
|
65 |
en_US_vctk_p268 |
|
|
66 |
en_US_vctk_p269 |
|
|
67 |
en_US_vctk_p270 |
|
|
68 |
en_US_vctk_p271 |
|
|
69 |
en_US_vctk_p272 |
|
|
70 |
en_US_vctk_p273 |
|
|
71 |
en_US_vctk_p274 |
|
|
72 |
en_US_vctk_p275 |
|
|
73 |
en_US_vctk_p276 |
|
|
74 |
en_US_vctk_p277 |
|
|
75 |
en_US_vctk_p278 |
|
|
76 |
en_US_vctk_p279 |
|
|
77 |
en_US_vctk_p280 |
|
|
78 |
en_US_vctk_p281 |
|
|
79 |
en_US_vctk_p282 |
|
|
80 |
en_US_vctk_p283 |
|
|
81 |
en_US_vctk_p284 |
|
|
82 |
en_US_vctk_p285 |
|
|
83 |
en_US_vctk_p286 |
|
|
84 |
en_US_vctk_p287 |
|
|
85 |
en_US_vctk_p288 |
|
|
86 |
en_US_vctk_p292 |
|
|
87 |
en_US_vctk_p293 |
|
|
88 |
en_US_vctk_p294 |
|
|
89 |
en_US_vctk_p295 |
|
|
90 |
en_US_vctk_p297 |
|
|
91 |
en_US_vctk_p298 |
|
|
92 |
en_US_vctk_p299 |
|
|
93 |
en_US_vctk_p300 |
|
|
94 |
en_US_vctk_p301 |
|
|
95 |
en_US_vctk_p302 |
|
|
96 |
en_US_vctk_p303 |
|
|
97 |
en_US_vctk_p304 |
|
|
98 |
en_US_vctk_p305 |
|
|
99 |
en_US_vctk_p306 |
|
|
100 |
en_US_vctk_p307 |
|
|
101 |
en_US_vctk_p308 |
|
|
102 |
en_US_vctk_p310 |
|
|
103 |
en_US_vctk_p311 |
|
|
104 |
en_US_vctk_p312 |
|
|
105 |
en_US_vctk_p313 |
|
|
106 |
en_US_vctk_p314 |
|
|
107 |
en_US_vctk_p316 |
|
|
108 |
en_US_vctk_p317 |
|
|
109 |
en_US_vctk_p318 |
|
|
110 |
en_US_vctk_p323 |
|
|
111 |
en_US_vctk_p326 |
|
|
112 |
en_US_vctk_p329 |
|
|
113 |
en_US_vctk_p336 |
|
|
114 |
en_US_vctk_p340 |
|
|
115 |
en_US_vctk_p341 |
|
|
116 |
en_US_vctk_p343 |
|
|
117 |
en_US_vctk_p345 |
|
|
118 |
en_US_vctk_p347 |
|
|
119 |
en_US_vctk_p351 |
|
|
120 |
en_US_vctk_p360 |
|
|
121 |
en_US_vctk_p361 |
|
|
122 |
en_US_vctk_p362 |
|
|
123 |
en_US_vctk_p363 |
|
|
124 |
en_US_vctk_p364 |
|
|
125 |
en_US_vctk_p374 |
|
|
126 |
en_US_vctk_p376 |
|
|
127 |
en_US_vctk_s5 |
|