Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Niger-Volta-LTI/yoruba-voice-speech-recorder

Domaine:

natural language processing

Type de record:

software
Créateur:
Nig
Hôte:
App for recording speech utterances dictated from text prompts. Speaker name, audio-recording path & prompt text are saved to a metadata file. Use it for building speech recognition and speech synthesis corpora # Yorùbá Voice Speech Recorder App for recording speech utterances dictated from text prompts. Speaker name, audio-recording path & prompt text are saved to a metadata file. Use it for building speech recognition and speech synthesis corpora for training and evaluation. ## Developer setup * **Prerequisites**: `git`, `python3` & `brew` * `git clone` this repo, `cd` into the repo directory * run installation script: `$ ./scripts/install.sh` * start app: `$ ./scripts/start.sh` ### Caveats `pyAudio`, the audio library used for recording audio, requires portaudio to be installed on the system. The easiest way is with brew ``` brew install portaudio ``` `portaudio` library may be installed in a custom location depending on your package manager `brew` or `macports`, or depending on your computer's hardware `arm64` vs Intel `x86`. In all cases, we must specify the location of headers and libraries, with `CPPFLAGS` & `LDFLAGS`. This is already done within the `./install.sh` script, but may need to be modified based on the above :point_up: For reference on - **M1 Macs**: `CPPFLAGS="-I/opt/homebrew/include" LDFLAGS="-L/opt/homebrew/lib" pip3 install -e .` - **Older Intel Macs**: `CPPFLAGS="-I/usr/local/include" LDFLAGS="-L/usr/local/lib" pip3 install -e .` - **Macports**: `CPPFLAGS="-I/opt/local/include" LDFLAGS="-L/opt/local/lib" pip3 install -e .` ## Developer py2app setup ``` $ python3 ./setup.py py2app -A # py2app uses setup to build an app bundle (.app) $ ./dist/Yorùbá\ Voice\ Speech\ recorder.app Voice\ Speech\ Recorder -p ~/github/yoruba-voice-speech-recorder/src/yoruba_voice_speech_recorder/prompts/timit.txt -d ~/Desktop/audio-data ``` ## Other packaging solutions * PyOxidizer * Nuitka * others like Typer, cx_freeze & shiv. ## License Distributed under the AGPL-3.0 license. See the LICENSE text file for more information. ## Acknowledgements This repo is based on a fork of github.com. We have …

Visit

github.com

Tasks

automatic speech recognitionspeech processing

Languages

Yoruba

Licenses

AGPL-3.0