Can Amazon Transcribe more than 4 langs in audio file at at time?

Question

Hi All,
My audio wav file containes more than 5 langs that are in supported list of amazon transcribe but when i upload to S# bucket and use  transcribe feature it is able to give me transcription in 4 langs only at time. start_transcription_job(TranscriptionJobName=job_name,Media={'MediaFileUri': job_uri},MediaFormat='wav',IdentifyMultipleLanguages=True,LanguageOptions=['ar-AE','tr-TR,ja-JP,pt-BR,es-ES']).

Can anyone please clarify is there any limit of no of langs identified in audio file.
Thanks in advance.

Answer

Hello,

If you choose to include language codes, you must include at least two. There's no limit on the number of language codes you can include, but we recommend using between two and five for optimal efficiency and accuracy.

With language identification, you have the option to include a list of languages you think may be present in your media. Including language options (LanguageOptions) restricts Amazon Transcribe to using only the languages that you specify when matching your audio to the correct language, which can speed up language identification and improve the accuracy associated with assigning the correct language dialect.

https://docs.aws.amazon.com/transcribe/latest/dg/lang-id-batch.html?icmpid=docs_console_unmapped#lang-id-batch-multi-language

Can Amazon Transcribe more than 4 langs in audio file at at time?

관련 콘텐츠