Skip to content

Commit 9ab7569

Browse files
authored
Merge pull request #280801 from eric-urban/eur/voices-locales
refresh voices locales
2 parents b11a9b4 + d5cc9e0 commit 9ab7569

File tree

3 files changed

+44
-44
lines changed

3 files changed

+44
-44
lines changed

articles/ai-services/speech-service/faq-stt.yml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -155,9 +155,9 @@ sections:
155155
answer: |
156156
Training a model with audio data can be a lengthy process. Depending on the amount of data, it can take several days to create a custom model. If it can't be finished within one week, the service might abort the training operation and report the model as failed.
157157
158-
In general, Speech service processes approximately 10 hours of audio data per day in regions that have dedicated hardware. It can process only about 1 hour of audio data per day in other regions. Training with text only is faster and ordinarily finishes within minutes.
158+
In general, Speech service processes approximately 10 hours of audio data per day in regions that have dedicated hardware. Training with text only is faster and ordinarily finishes within minutes.
159159
160-
Use one of the regions where dedicated hardware is available for training. The Speech service uses up to 20 hours of audio for training in these regions. In other regions, the Speech service uses up to 8 hours.
160+
Use one of the regions where dedicated hardware is available for training. The Speech service uses up to 20 hours of audio for training in these regions.
161161
162162
- name: Accuracy testing
163163
questions:

articles/ai-services/speech-service/includes/language-support/stt.md

Lines changed: 41 additions & 41 deletions
Original file line numberDiff line numberDiff line change
@@ -10,32 +10,32 @@ ms.author: eur
1010
| ----- | ----- | ----- |
1111
| `af-ZA` | Afrikaans (South Africa) | Plain text |
1212
| `am-ET` | Amharic (Ethiopia) | Plain text |
13-
| `ar-AE` | Arabic (United Arab Emirates) | Plain text |
13+
| `ar-AE` | Arabic (United Arab Emirates) | Audio + human-labeled transcript<br/><br/>Plain text |
1414
| `ar-BH` | Arabic (Bahrain) | Audio + human-labeled transcript<br/><br/>Plain text |
1515
| `ar-DZ` | Arabic (Algeria) | Audio + human-labeled transcript<br/><br/>Plain text |
1616
| `ar-EG` | Arabic (Egypt) | Audio + human-labeled transcript<br/><br/>Plain text |
17-
| `ar-IL` | Arabic (Israel) | Plain text |
18-
| `ar-IQ` | Arabic (Iraq) | Plain text |
19-
| `ar-JO` | Arabic (Jordan) | Plain text |
20-
| `ar-KW` | Arabic (Kuwait) | Plain text |
21-
| `ar-LB` | Arabic (Lebanon) | Plain text |
22-
| `ar-LY` | Arabic (Libya) | Plain text |
17+
| `ar-IL` | Arabic (Israel) | Audio + human-labeled transcript<br/><br/>Plain text |
18+
| `ar-IQ` | Arabic (Iraq) | Audio + human-labeled transcript<br/><br/>Plain text |
19+
| `ar-JO` | Arabic (Jordan) | Audio + human-labeled transcript<br/><br/>Plain text |
20+
| `ar-KW` | Arabic (Kuwait) | Audio + human-labeled transcript<br/><br/>Plain text |
21+
| `ar-LB` | Arabic (Lebanon) | Audio + human-labeled transcript<br/><br/>Plain text |
22+
| `ar-LY` | Arabic (Libya) | Audio + human-labeled transcript<br/><br/>Plain text |
2323
| `ar-MA` | Arabic (Morocco) | Audio + human-labeled transcript<br/><br/>Plain text |
24-
| `ar-OM` | Arabic (Oman) | Plain text |
25-
| `ar-PS` | Arabic (Palestinian Authority) | Plain text |
26-
| `ar-QA` | Arabic (Qatar) | Plain text |
24+
| `ar-OM` | Arabic (Oman) | Audio + human-labeled transcript<br/><br/>Plain text |
25+
| `ar-PS` | Arabic (Palestinian Authority) | Audio + human-labeled transcript<br/><br/>Plain text |
26+
| `ar-QA` | Arabic (Qatar) | Audio + human-labeled transcript<br/><br/>Plain text |
2727
| `ar-SA` | Arabic (Saudi Arabia) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Phrase list |
28-
| `ar-SY` | Arabic (Syria) | Plain text |
28+
| `ar-SY` | Arabic (Syria) | Audio + human-labeled transcript<br/><br/>Plain text |
2929
| `ar-TN` | Arabic (Tunisia) | Audio + human-labeled transcript<br/><br/>Plain text |
3030
| `ar-YE` | Arabic (Yemen) | Audio + human-labeled transcript<br/><br/>Plain text |
3131
| `az-AZ` | Azerbaijani (Latin, Azerbaijan) | Plain text |
3232
| `bg-BG` | Bulgarian (Bulgaria) | Plain text |
3333
| `bn-IN` | Bengali (India) | Plain text |
3434
| `bs-BA` | Bosnian (Bosnia and Herzegovina) | Plain text |
3535
| `ca-ES` | Catalan | Plain text<br/><br/>Pronunciation |
36-
| `cs-CZ` | Czech (Czechia) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Pronunciation |
36+
| `cs-CZ` | Czech (Czechia) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
3737
| `cy-GB` | Welsh (United Kingdom) | Plain text |
38-
| `da-DK` | Danish (Denmark) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation |
38+
| `da-DK` | Danish (Denmark) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation |
3939
| `de-AT` | German (Austria) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
4040
| `de-CH` | German (Switzerland) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Pronunciation<br/><br/>Phrase list |
4141
| `de-DE` | German (Germany) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
@@ -44,17 +44,17 @@ ms.author: eur
4444
| `en-CA` | English (Canada) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
4545
| `en-GB` | English (United Kingdom) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
4646
| `en-GH` | English (Ghana) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
47-
| `en-HK` | English (Hong Kong SAR) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation |
48-
| `en-IE` | English (Ireland) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
47+
| `en-HK` | English (Hong Kong SAR) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation |
48+
| `en-IE` | English (Ireland) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
4949
| `en-IN` | English (India) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
5050
| `en-KE` | English (Kenya) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
51-
| `en-NG` | English (Nigeria) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation |
52-
| `en-NZ` | English (New Zealand) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation |
53-
| `en-PH` | English (Philippines) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation |
54-
| `en-SG` | English (Singapore) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation |
51+
| `en-NG` | English (Nigeria) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation |
52+
| `en-NZ` | English (New Zealand) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation |
53+
| `en-PH` | English (Philippines) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation |
54+
| `en-SG` | English (Singapore) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation |
5555
| `en-TZ` | English (Tanzania) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
5656
| `en-US` | English (United States) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
57-
| `en-ZA` | English (South Africa) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Pronunciation<br/><br/>Phrase list |
57+
| `en-ZA` | English (South Africa) | Audio + human-labeled transcript<br/><br/>Audio<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Pronunciation<br/><br/>Phrase list |
5858
| `es-AR` | Spanish (Argentina) | Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
5959
| `es-BO` | Spanish (Bolivia) | Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
6060
| `es-CL` | Spanish (Chile) | Plain text<br/><br/>Structured text<br/><br/>Pronunciation |
@@ -81,9 +81,9 @@ ms.author: eur
8181
| `eu-ES` | Basque | Plain text |
8282
| `fa-IR` | Persian (Iran) | Plain text |
8383
| `fi-FI` | Finnish (Finland) | Plain text<br/><br/>Output format<br/><br/>Pronunciation |
84-
| `fil-PH` | Filipino (Philippines) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Pronunciation |
85-
| `fr-BE` | French (Belgium) | Audio + human-labeled transcript<br/><br/>Plain text |
86-
| `fr-CA` | French (Canada)<sup>1</sup> | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
84+
| `fil-PH` | Filipino (Philippines) | Plain text<br/><br/>Pronunciation |
85+
| `fr-BE` | French (Belgium) | Plain text |
86+
| `fr-CA` | French (Canada)<sup>1</sup> | Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
8787
| `fr-CH` | French (Switzerland) | Plain text<br/><br/>Pronunciation |
8888
| `fr-FR` | French (France) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
8989
| `ga-IE` | Irish (Ireland) | Plain text<br/><br/>Pronunciation |
@@ -92,11 +92,11 @@ ms.author: eur
9292
| `he-IL` | Hebrew (Israel) | Audio + human-labeled transcript<br/><br/>Plain text |
9393
| `hi-IN` | Hindi (India) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Output format<br/><br/>Phrase list |
9494
| `hr-HR` | Croatian (Croatia) | Plain text<br/><br/>Pronunciation |
95-
| `hu-HU` | Hungarian (Hungary) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Pronunciation |
95+
| `hu-HU` | Hungarian (Hungary) | Plain text<br/><br/>Pronunciation |
9696
| `hy-AM` | Armenian (Armenia) | Plain text |
9797
| `id-ID` | Indonesian (Indonesia) | Plain text<br/><br/>Pronunciation<br/><br/>Phrase list |
9898
| `is-IS` | Icelandic (Iceland) | Plain text |
99-
| `it-CH` | Italian (Switzerland) | Audio + human-labeled transcript<br/><br/>Plain text |
99+
| `it-CH` | Italian (Switzerland) | Plain text |
100100
| `it-IT` | Italian (Italy) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
101101
| `ja-JP` | Japanese (Japan) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Phrase list |
102102
| `jv-ID` | Javanese (Latin, Indonesia) | Plain text |
@@ -112,18 +112,18 @@ ms.author: eur
112112
| `ml-IN` | Malayalam (India) | Plain text |
113113
| `mn-MN` | Mongolian (Mongolia) | Plain text |
114114
| `mr-IN` | Marathi (India) | Plain text |
115-
| `ms-MY` | Malay (Malaysia) | Audio + human-labeled transcript<br/><br/>Plain text |
115+
| `ms-MY` | Malay (Malaysia) | Plain text |
116116
| `mt-MT` | Maltese (Malta) | Plain text |
117117
| `my-MM` | Burmese (Myanmar) | Plain text |
118-
| `nb-NO` | Norwegian Bokmål (Norway) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Output format |
118+
| `nb-NO` | Norwegian Bokmål (Norway) | Plain text<br/><br/>Output format |
119119
| `ne-NP` | Nepali (Nepal) | Plain text |
120120
| `nl-BE` | Dutch (Belgium) | Plain text |
121-
| `nl-NL` | Dutch (Netherlands) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
121+
| `nl-NL` | Dutch (Netherlands) | Plain text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
122122
| `pa-IN` | Punjabi (India) | Audio + human-labeled transcript |
123-
| `pl-PL` | Polish (Poland) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
123+
| `pl-PL` | Polish (Poland) | Plain text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
124124
| `ps-AF` | Pashto (Afghanistan) | Plain text |
125125
| `pt-BR` | Portuguese (Brazil) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
126-
| `pt-PT` | Portuguese (Portugal) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
126+
| `pt-PT` | Portuguese (Portugal) | Plain text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
127127
| `ro-RO` | Romanian (Romania) | Plain text<br/><br/>Pronunciation |
128128
| `ru-RU` | Russian (Russia) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Phrase list |
129129
| `si-LK` | Sinhala (Sri Lanka) | Plain text |
@@ -133,23 +133,23 @@ ms.author: eur
133133
| `sq-AL` | Albanian (Albania) | Plain text |
134134
| `sr-RS` | Serbian (Cyrillic, Serbia) | Plain text |
135135
| `sv-SE` | Swedish (Sweden) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Output format<br/><br/>Pronunciation<br/><br/>Phrase list |
136-
| `sw-KE` | Swahili (Kenya) | Audio + human-labeled transcript<br/><br/>Plain text |
137-
| `sw-TZ` | Swahili (Tanzania) | Audio + human-labeled transcript<br/><br/>Plain text |
136+
| `sw-KE` | Kiswahili (Kenya) | Plain text |
137+
| `sw-TZ` | Kiswahili (Tanzania) | Plain text |
138138
| `ta-IN` | Tamil (India) | Plain text |
139139
| `te-IN` | Telugu (India) | Plain text |
140140
| `th-TH` | Thai (Thailand) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Phrase list |
141141
| `tr-TR` | Turkish (Türkiye) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format |
142142
| `uk-UA` | Ukrainian (Ukraine) | Plain text |
143143
| `ur-IN` | Urdu (India) | Audio + human-labeled transcript |
144144
| `uz-UZ` | Uzbek (Latin, Uzbekistan) | Plain text |
145-
| `vi-VN` | Vietnamese (Vietnam) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Phrase list |
146-
| `wuu-CN` | Chinese (Wu, Simplified) | Audio + human-labeled transcript<br/><br/>Plain text |
147-
| `yue-CN` | Chinese (Cantonese, Simplified) | Audio + human-labeled transcript<br/><br/>Plain text |
148-
| `zh-CN` | Chinese (Mandarin, Simplified) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Phrase list |
149-
| `zh-CN-shandong` | Chinese (Jilu Mandarin, Simplified) | Audio + human-labeled transcript<br/><br/>Plain text |
150-
| `zh-CN-sichuan` | Chinese (Southwestern Mandarin, Simplified) | Audio + human-labeled transcript<br/><br/>Plain text |
145+
| `vi-VN` | Vietnamese (Vietnam) | Plain text<br/><br/>Phrase list |
146+
| `wuu-CN` | Chinese (Wu, Simplified) | Plain text |
147+
| `yue-CN` | Chinese (Cantonese, Simplified) | Plain text |
148+
| `zh-CN` | Chinese (Mandarin, Simplified) | Plain text<br/><br/>Structured text<br/><br/>Output format<br/><br/>Phrase list |
149+
| `zh-CN-shandong` | Chinese (Jilu Mandarin, Simplified) | Plain text |
150+
| `zh-CN-sichuan` | Chinese (Southwestern Mandarin, Simplified) | Plain text |
151151
| `zh-HK` | Chinese (Cantonese, Traditional) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Output format<br/><br/>Phrase list |
152-
| `zh-TW` | Chinese (Taiwanese Mandarin, Traditional) | Audio + human-labeled transcript<br/><br/>Plain text<br/><br/>Phrase list |
153-
| `zu-ZA` | Zulu (South Africa) | Plain text |
152+
| `zh-TW` | Chinese (Taiwanese Mandarin, Traditional) | Plain text<br/><br/>Phrase list |
153+
| `zu-ZA` | isiZulu (South Africa) | Plain text |
154154

155-
<sup>1</sup> The model is bilingual and also supports English.
155+
<sup>1</sup> The model is bilingual and also supports English.

articles/ai-services/speech-service/regions.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -61,7 +61,7 @@ The following regions are supported for Speech service features such as speech t
6161
| US | West US 2 | `westus2` <sup>1,2,4,5,7,10</sup> |
6262
| US | West US 3 | `westus3` <sup>3</sup> |
6363

64-
<sup>1</sup> The region has dedicated hardware for custom speech training. If you plan to train a custom model with audio data, use one of the regions with dedicated hardware for faster training. Then you can [copy the trained model](how-to-custom-speech-train-model.md#copy-a-model) to another region.
64+
<sup>1</sup> The region has dedicated hardware for custom speech training. If you plan to train a custom model with audio data, you must use one of the regions with dedicated hardware. Then you can [copy the trained model](how-to-custom-speech-train-model.md#copy-a-model) to another region.
6565

6666
<sup>2</sup> The region is available for custom neural voice training. You can copy a trained neural voice model to other regions for deployment.
6767

0 commit comments

Comments
 (0)