NVIDIA open-sourced the speech transcription model Nemotron 3.5 Transcribe, supporting 40 languages and 8 speaker separation.
NVIDIA launched the open-weight speech transcription model Nemotron 3.5 Transcribe on October 28, integrating transcription, speaker attribution, translation, and audio Q&A, using the MoE architecture, with total parameters of about 34 billion and activation parameters of about 4.3 billion, capable of processing the longest recording of 1 hour, supporting transcription of 40 languages, and distinguishing up to 8 speakers.
NVIDIA open-sourced the speech transcription model, disclosing parameter scale, multilingual and speaker separation capabilities, and benchmark results, allowing comparison with existing open-source ASR solutions.
Same story3 other outlets also reported this
- TechCrunch · AI··First
NVIDIA releases open-source speech-to-text model Nemotron 3.5 Transcribe
- The Decoder··+50 min
Nvidia releases open-source speech model Nemotron 3.5 Transcribe, integrating transcription, translation, and speaker recognition
- MarkTechPost··+13 h 41 min
NVIDIA released the open-source speech model Nemotron 3.5 Transcribe, supporting transcription of 40 languages.
Adds:active parameters about 4B; offline operation
- ITHome · AI··+16 h 31 min·Reading now
NVIDIA open-sourced the speech transcription model Nemotron 3.5 Transcribe, supporting 40 languages and 8 speaker separation.
In order of publication · later reports are added as they appear · Compared by AI from each outlet’s title and summary
Source: ITHome · AI · ithome.com