SELMA Open Source Platform (UC0)
- Authors
- Goško, Didzis and Bārzdiņš, Guntis
- Item identifier
- http://hdl.handle.net/20.500.12574/97
- Project URL
- https://selma-project.eu
- Demo URL
- https://selma.ailab.lv
- Referenced by
-
https://selma-project.eu/2023/10/18/the-selma-open-source-platform/
https://github.com/SELMA-project/UC0-OpenSource
- Date issued
- 2024-02
- Type
- toolService
- Description
- The SELMA Open-Source Software (OSS) offers effective means to test and compare the performance of various language models used in multilingual media monitoring and content production. The SELMA OSS Platform (also referred to as Use Case 0, UC0, or The Basic Testing and Configuration Interface) provides: * automatic speech recognition (ASR) from audio/video files, * punctuation and capitalization of the transcribed text, * machine translation (MT) into a target language, * text-to-speech synthesis (TTS) and voice-over generation. To provide this functionality, the demonstrator release uses these multilingual open source models: OpenAI Whisper (ASR), Meta MMS (TTS, ASR), Meta M2M-100 (MT). Thus, it facilitates easy access to such open large language models. The SELMA Platform can be used not only by developers in order to combine and test alternative language models before they are integrated into the end-user applications – it can also be used as an entry-level application by journalists and media producers themselves to transcribe their recordings, generate subtitles and voice-over, or to generate a podcast from an input text. The demonstrator of the SELMA OSS Platform does not require registration and authentication nor does it store any content, original or generated, after the session is closed by the user.
- Publisher
- AiLab IMCS UL
- Acknowledgement
-
European Commission
Project code: 957017
Project name: SELMA – Stream Learning for Multilingual Knowledge Transfer
- Collection(s)
-
