MLS-C01 · Question #243
A sports broadcasting company is planning to introduce subtitles in multiple languages for a live broadcast. The commentary is in English. The company needs the transcriptions to appear on screen in…
The correct answer is B. Amazon Transcribe with custom language models E. Amazon Translate. Option B (Amazon Transcribe with custom language models): Custom language models (CLMs) in Transcribe are trained on domain-specific text data (sports commentary, player names, locations, team names) to significantly improve transcription accuracy beyond what custom…
Question
A sports broadcasting company is planning to introduce subtitles in multiple languages for a live broadcast. The commentary is in English. The company needs the transcriptions to appear on screen in French or Spanish, depending on the broadcasting country. The transcriptions must be able to capture domain-specific terminology, names, and locations based on the commentary context. The company needs a solution that can support options to provide tuning data. Which combination of AWS services and features will meet these requirements with the LEAST operational overhead? (Choose two.)
Options
- AAmazon Transcribe with custom vocabularies
- BAmazon Transcribe with custom language models
- CAmazon SageMaker Seq2Seq
- DAmazon SageMaker with Hugging Face Speech2Text
- EAmazon Translate
How the community answered
(41 responses)- A2% (1)
- B80% (33)
- C7% (3)
- D10% (4)
Explanation
Option B (Amazon Transcribe with custom language models): Custom language models (CLMs) in Transcribe are trained on domain-specific text data (sports commentary, player names, locations, team names) to significantly improve transcription accuracy beyond what custom vocabularies alone can achieve. CLMs handle novel terminology in context, making them the right choice for specialized sports broadcasting. Option E (Amazon Translate): After transcription, Amazon Translate converts the English transcript to French or Spanish in real time - it is a fully managed neural translation service that requires no custom training for general language pairs. Option A (custom vocabularies) handles individual words/phrases but lacks the contextual modeling of CLMs. Options C and D (SageMaker Seq2Seq, Hugging Face Speech2Text) require custom model training, data preparation, and infrastructure management - much higher operational overhead than managed AWS services.
Topics
Community Discussion
No community discussion yet for this question.