Multimarket studies
This article outlines best practices and further information for researchers conducting multi market studies. Please refer to specific guides on Live Interviews and Online Qualitative for general advice.
Which languages are supported for transcription?
This section outlines which languages are currently supported for transcription (speech to text).
Live Interviews
We are currently working on extending support for additional languages via out Zoom, Teams and Google Meet integration
For live interviews CoLoop currently supports the following languages with near-human quality (more detail available here)
Languages Supported For Transcription
Languages Supported For Transcription
Language | Language Code |
---|---|
๐บ๐ธ US English | en_us |
๐ฆ๐บ Australian English | en_au |
๐ฌ๐ง UK English | en_uk |
๐ช๐ธ Spanish | es |
๐ซ๐ท French | fr |
๐ฉ๐ช German | de |
๐ฎ๐น Italian | it |
๐ต๐น Portuguese | pt |
๐ณ๐ฑ Dutch | nl |
๐ซ๐ฎ Finnish | fi |
๐ต๐ฑ Polish | pl |
๐น๐ท Turkish | tr |
๐ท๐บ Russian | ru |
๐ฎ๐ณ Hindi | hi |
๐ฏ๐ต Japanese | ja |
๐จ๐ณ Chinese | zh-CN |
๐ป๐ณ Vietnamese | vi |
๐ฐ๐ท Korean | ko |
Online Qual
For online qual CoLoop currently supports the following languages. More niche languages such as Welsh may have variable quality due to the availability of training data (more details here).
Europe
Europe
British English ๐ฌ๐ง | Greek ๐ฌ๐ท |
Spanish ๐ช๐ธ | Hungarian ๐ญ๐บ |
French ๐ซ๐ท | Icelandic ๐ฎ๐ธ |
German ๐ฉ๐ช | Latin ๐ป๐ฆ |
Italian ๐ฎ๐น | Latvian ๐ฑ๐ป |
Portuguese ๐ต๐น | Lithuanian ๐ฑ๐น |
Dutch ๐ณ๐ฑ | Luxembourgish ๐ฑ๐บ |
Albanian ๐ฆ๐ฑ | Macedonian ๐ฒ๐ฐ |
Basque ๐ช๐ธ | Danish ๐ฉ๐ฐ |
Breton ๐ซ๐ท | Estonian ๐ช๐ช |
Catalan ๐ช๐ธ | Faroese ๐ซร |
Croatian ๐ญ๐ท | Finnish ๐ซ๐ฎ |
Czech ๐จZ | Galician ๐ช๐ธ |
Americas & Oceania
Americas & Oceania
Global English ๐บ๐ธ | Greenlandic |
Australian English ๐ฆ๐บ | Inuktitut |
American English ๐บ๐ธ | Navajo |
Haitian ๐ญ๐น | Mapudungun |
Hawaiian ๐บ๐ธ | Cherokee |
Maori ๐ณ๐ฟ | Aymara |
Portuguese ๐ต๐น (considering Brazilian Portuguese) | Nahuatl |
Spanish ๐ช๐ธ (considering Latin American Spanish) | Quechua |
Dutch ๐ณ๐ฑ (considering Caribbean Dutch) | Guarani |
English variants used in North and South America | Yucatec Maya |
French variants used in North and South America | Tzotzil |
Creole languages (e.g., Haitian Creole) | Arawakan languages |
Indigenous languages (e.g., Quechua, Guarani) | Tupian languages |
Middle East & Asia
Middle East & Asia
Assamese ๐ฎ๐ณ | Arabic ๐ธ๐ฆ |
Bengali ๐ง๐ฉ | Hebrew ๐ฎ๐ฑ |
Gujarati ๐ฎ๐ณ | Persian ๐ฎ๐ท |
Hindi ๐ฎ๐ณ | Sindhi ๐ต๐ฐ |
Kannada ๐ฎ๐ณ | Sinhala ๐ฑ๐ฐ |
Malayalam ๐ฎ๐ณ | Tamil ๐ฎ๐ณ |
Marathi ๐ฎ๐ณ | Telugu ๐ฎ๐ณ |
Nepali ๐ณ๐ต | Urdu ๐ต๐ฐ |
Panjabi ๐ฎ๐ณ | Burmese ๐ฒ๐ฒ |
Sanskrit ๐ฎ๐ณ | Cambodian (Khmer) ๐ฐ๐ญ |
Indonesian ๐ฎ๐ฉ | Lao ๐ฑ๐ฆ |
Javanese ๐ฎ๐ฉ | Malay ๐ฒ๐พ |
Sundanese ๐ฎ๐ฉ | Tagalog ๐ต๐ญ |
Thai ๐น๐ญ | Vietnamese ๐ป๐ณ |
Africa
Africa
Language | Language |
---|---|
Afrikaans ๐ฟ๐ฆ | Wolof |
Amharic ๐ช๐น | Kikuyu |
Hausa ๐ณ๏ฟฝ๐ฌ | Luganda |
Malagasy ๐ฒ๐ฌ | Tigrinya |
Swahili ๐ฐ๐ช | Kinyarwanda |
Somali ๐ธ๐ด | Kirundi |
Yoruba ๐ณ๏ฟฝ๐ฌ | Chichewa |
Zulu ๐ฟ๏ฟฝ๐ฆ | Ndebele |
Shona ๐ฟ๏ฟฝ๐ผ | Oshiwambo |
Berber languages | Swati |
Akan | Xhosa |
Igbo | Sesotho |
Fula | Setswana |
When transcribing these files in CoLoop you should click detect language
if there are multiple languages present in the online qual upload.
Which languages are supported for translation?
This section outlines which languages are currently supported for translation (Non-English to English). Transcripts do not need to be translated in order to conduct analysis however quotes and transcripts will be shown in the native language.
Live Interviews & Online Qual
For live interviews CoLoop currently supports the following languages for translation:
Languages Supported For Translation
Languages Supported For Translation
Language | Language Code |
---|---|
๐ฆ๐ช Arabic | ar |
๐ง๐ฌ Bulgarian | bg |
๐จ๐ณ Chinese | zh |
๐จ๐ฟ Czech | cs |
๐ฉ๐ฐ Danish | da |
๐ณ๐ฑ Dutch | nl |
๐บ๐ธ English | en |
๐ช๐ช Estonian | et |
๐ซ๐ฎ Finnish | fi |
๐ซ๐ท French | fr |
๐ฉ๐ช German | de |
๐ฌ๐ท Greek | el |
๐ญ๐บ Hungarian | hu |
๐ฎ๐ฉ Indonesian | id |
๐ฎ๐น Italian | it |
๐ฏ๐ต Japanese | ja |
๐ฐ๐ท Korean | ko |
๐ฑ๐ป Latvian | lv |
๐ฑ๐น Lithuanian | lt |
๐ณ๐ด Norwegian | no |
๐ต๐ฑ Polish | pl |
๐ต๐น Portuguese | pt |
๐ท๐ด Romanian | ro |
๐ท๐บ Russian | ru |
๐ธ๐ฐ Slovak | sk |
๐ธ๐ฎ Slovenian | sl |
๐ช๐ธ Spanish | es |
๐ธ๐ช Swedish | sv |
๐น๐ท Turkish | tr |
๐บ๐ฆ Ukrainian | uk |
What if my language is supported for translation but not transcription?
- Translation within CoLoop can also be applied to txt and docx files.
- If you are working in a language we support for translation but not transcription e.g. Arabic you can upload 3rd party transcripts in the native language and translate them in CoLoop.
- Be sure to checkout our formatting guides to ensure your native language transcripts are properly processed (more details here).
Simultaneous Translation
Working with SimTran files in CoLoop can present challenges as they contain only one speaker. In this scenario we recommend using the original language file if it is supported.
SimTran files can be uploaded to CoLoop but please consider the following.
- Theme counts may not be accurate particularly if the interview involved more than 2 speakers
- CoLoop will not be able to as accurately distinguish moderator and participant statements so you will see moderator highlighted in the evidence panel
- These can be effectively used for simple use cases like summaries and finding quotes
For more information please refer to this guide.
Using 3rd party transcripts from focus groups
In some cases 3rd party transcripts of focus groups may not contain speaker level identification, only moderator and participants.
- Here we recommend merging together participants into a generic speaker label
- You can do this by running a find & replace on all instances of respondent
- And replacing them with something generic like โFocus Group 2 Participantsโ
- This approach will come with the drawback that theme counts will no longer be accurate
- It will also only be possible to summarise responses from the concensus of the whole group
Example
Original Transcript
Updated Transcript