descriptinc / gentle
gentle forced aligner
☆11Updated 10 months ago
Alternatives and similar repositories for gentle:
Users that are interested in gentle are comparing it to the libraries listed below
- Experiment in automatic insertion of timed transcript corrections☆21Updated 7 years ago
- 🐍 Coqui's machine learning job scheduler☆32Updated 3 years ago
- Web app for keyword spotting using TensorflowJS☆71Updated 2 years ago
- Demonstration of gpt-2 model with flask+uwsgi+nginx in web environment containerized in docker for quick deployment.☆13Updated last year
- Experiments with generating GPT-2 fanfiction on specified topics.☆11Updated 5 years ago
- Work in progress - BBC News Labs digital paper edit project - React Client☆45Updated last year
- GUI text-based speech and music editor for creating radio/audio stories☆77Updated 2 years ago
- Make musical loops in the browser using WaveGAN, GANSynth, and MusicVAE☆34Updated 2 years ago
- 🐸TTS recipes for different datasets☆86Updated 2 years ago
- Live Audio MFCC Visualization in the browser using Web Audio API - https://pulakk.github.io/Live-Audio-MFCC/tutorial☆41Updated 5 years ago
- Implement SSML parsing for Web Speech API☆36Updated 4 years ago
- Simple text to phonemes converter for multiple languages☆20Updated 2 years ago
- ☆21Updated 7 years ago
- Tensorflow implementation of DiffWave: A Versatile Diffusion Model for Audio Synthesis☆40Updated 4 years ago
- INACTIVE - http://mzl.la/ghe-archive - Tools to create ARPA models from cmu pocketsphinx dictionaries for proper g2p generation☆21Updated 5 years ago
- SailAlign is an open-source software toolkit for robust long speech-text alignment implementing an adaptive, iterative speech recognition…☆98Updated 2 years ago
- ☆16Updated last year
- automatically align transcribed audio and generate a wav2letter training corpus☆36Updated last year
- node version of stt-align https://github.com/bbc/stt-align by Chris Baume - R&D.☆13Updated last year
- Labeled data for homograph disambiguation☆56Updated last year
- ☆82Updated 6 years ago
- lightweight JavaScript for presenting hypertranscripts☆14Updated 8 years ago
- 🎸 pop music transformer.☆34Updated 5 years ago
- Pytorch implementation of Deepmind's WaveRNN model☆13Updated 4 years ago
- generate rules from lists of words☆16Updated 3 years ago
- An even smaller speech recognizer / force aligner☆32Updated 3 months ago
- Tracking states of the arts and recent results (bibliography) on sound tasks.☆32Updated 2 years ago
- Code base for WaveTransformer: A novel architecture for automated audio captioning☆43Updated 4 years ago
- A collection of pre-built speech synthesis settings used to convey emotion☆11Updated 5 years ago
- DeepSpeech based forced alignment tool☆237Updated 4 years ago