Commit History

  1. EchoScript : services\translation.py , Fix: services/translation.py now loads MarianMT directly via AutoModelForSeq2SeqLM + AutoTokenizer and calls model.generate() itself, bypassing the removed pipeline() task wrapper entirely. This is the path the official MarianMT docs use now too, so it's not a workaround you'll need to revisit on the next transformers release.

    usertea
    0f04f89
  2. EchoScript : New UI

    usertea
    abbbd7b
  3. EchoScript : New Architecture

    usertea
    7d761b6
  4. \EchoScript : Multi-language transcription, Automatic language detection, Translation to English, Batch processing (multiple audio files), TXT export, SRT export, VTT export, CPU-only execution, Faster-Whisper (Model Initialization Improvement)

    usertea
    7e1a6e6
  5. \EchoScript : Multi-language transcription, Automatic language detection, Translation to English, Batch processing (multiple audio files), TXT export, SRT export, VTT export, CPU-only execution, Faster-Whisper (Model Initialization Improvement)

    usertea
    18a6a4c
  6. \EchoScript : Multi-language transcription, Automatic language detection, Translation to English, Batch processing (multiple audio files), TXT export, SRT export, VTT export, CPU-only execution, Faster-Whisper (Model Initialization Improvement)

    usertea
    5c9196d
  7. EchoScript : Add ffmpeg

    usertea
    b352be4
  8. EchoScript : requirements.txt , Add faster_whisper

    usertea
    5cf7618
  9. EchoScript : remove typo

    usertea
    586b3e7
  10. EchoScript : Add application file

    usertea
    8ae702a
  11. initial commit

    Verified signature
    cc4eaac