Skip to content
vfernandezg.devProjectsContact
All projects

LocalSpeakerTranscriber

Local pipeline that turns an audio recording into a transcript attributed to each speaker, without sending the audio to external services.

Gradio interface of LocalSpeakerTranscriber with the audio upload, the Whisper model and speaker settings, the transcript box and the CSV, TXT and JSON downloads
Role
Author
Period
Jun 2026
Status
Completed
Stack
  • Python
  • faster-whisper
  • NVIDIA NeMo
  • Gradio
  • ffmpeg

A personal tool. It takes a recording and produces a transcript in which every line carries a speaker, a timestamp and a confidence value. Everything runs locally; the models are downloaded once, on first use.

How it works

  1. Audio preparation. ffprobe inspects the file and ffmpeg converts it to 16 kHz mono, with a duration check afterwards.
  2. Diarization. NVIDIA NeMo’s clustering diarizer decides who speaks when, using MarbleNet for voice activity, TitaNet embeddings and spectral clustering.
  3. Transcription. faster-whisper produces timed text segments.
  4. Alignment. This step is my own. For each text segment it adds up the overlap with every speaker and picks the largest. It records a confidence value, flags ambiguous segments together with the runner-up, and marks segments with no overlap as unknown.
  5. Outputs. A CSV, a JSON file, a Markdown report with each speaker’s share and low-confidence warnings, and a dialogue text file.

It has a command line with nine subcommands and a Gradio interface that listens on localhost only.

Engineering practice

  • Machine-learning imports are lazy, so the command line, the alignment and the exports run and are tested without PyTorch.
  • A Windows setup script with a CUDA or CPU switch, and a troubleshooting guide.

Limits

Speakers are attributed per segment, not per word, and overlapping speech is ignored. I have not published accuracy or speed figures. The models are NVIDIA’s and OpenAI’s Whisper; my work is the pipeline around them.