tomatocream/cohere-transcribe
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
21 Commits 2 Branches 0 Tags
master
T
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE
tomatocream 58fa7526fb feat: add --normalize compressor + limiter for input audio 
Adds a feedforward dynamic range compressor with a brick-wall limiter
applied in the audio callback. Quiet speech gets +12 dB makeup gain,
loud bursts are attenuated 4:1 above -20 dBFS, and the output is
hard-limited at -1 dBFS so nothing clips. Enabled via --normalize/-n
on `cohere on` and `cohere transcribe`.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-06 22:56:21 +08:00
docs/superpowers
Add implementation plan for live streaming transcription
2026-05-29 02:42:00 +08:00
notebooks
feat: filter short audio segments (mic bumps) and add debug notebook
2026-06-01 16:16:31 +08:00
src/cohere_transcribe
feat: add --normalize compressor + limiter for input audio
2026-06-06 22:56:21 +08:00
tests
refactor: restructure project into src layout with proper packaging
2026-05-30 00:45:56 +08:00
.envrc
Add design spec for live streaming microphone transcription
2026-05-29 02:38:05 +08:00
.gitignore
refactor: restructure project into src layout with proper packaging
2026-05-30 00:45:56 +08:00
.python-version
Add Cohere Transcribe demo with uv + Python 3.14
2026-05-26 01:35:10 +08:00
CLAUDE.md
Initial commit: add CLAUDE.md and transcribe.py
2026-05-31 01:05:48 +08:00
flake.lock
fix: add portaudio to LD_LIBRARY_PATH and add flake lockfile
2026-05-30 00:42:36 +08:00
flake.nix
feat: add Typer CLI with daemon mode and wtype keyboard injection
2026-05-30 21:09:32 +08:00
pyproject.toml
feat: filter short audio segments (mic bumps) and add debug notebook
2026-06-01 16:16:31 +08:00
README.md
Add Cohere Transcribe demo with uv + Python 3.14
2026-05-26 01:35:10 +08:00
transcribe.py
Initial commit: add CLAUDE.md and transcribe.py
2026-05-31 01:05:48 +08:00
uv.lock
feat: filter short audio segments (mic bumps) and add debug notebook
2026-06-01 16:16:31 +08:00

README.md

The file is empty.
Reference in New Issue View Git Blame Copy Permalink
S
Description
Live speech-to-text using Cohere ASR model
Readme MIT 11 MiB