festvox / festival
Festival Speech Synthesis System
☆397Updated last year
Related projects ⓘ
Alternatives and complementary repositories for festival
- A small fast portable speech synthesis system☆886Updated 4 months ago
- Festvox voice building tools☆99Updated 6 months ago
- MBROLA is a speech synthesizer based on the concatenation of diphones☆236Updated 9 months ago
- A tokenizer, text cleaner, and phonemizer for many human languages.☆285Updated this week
- Data files of mbrola speech synthesizer voices☆117Updated 4 years ago
- Text to Speech engine based on the Tacotron architecture, initially implemented by Keith Ito.☆580Updated 3 years ago
- Crystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with SSML specification as interface.☆225Updated 4 years ago
- Phonetisaurus G2P☆453Updated 5 months ago
- Mycroft's TTS engine, based on CMU's Flite (Festival Lite)☆825Updated 2 years ago
- A suite of speech signal processing tools☆226Updated this week
- Edinburgh Speech Tools☆56Updated last year
- Open tools and data for cloudless automatic speech recognition☆443Updated 3 years ago
- Large, modern dataset for speech recognition☆646Updated 8 months ago
- 🐸STT integration examples☆121Updated 2 years ago
- CMU US English Dictionary☆624Updated 5 months ago
- GStreamer plugin around Kaldi's online neural network decoder☆185Updated 4 years ago
- Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time☆339Updated last year
- CMU Wilderness Multilingual Speech Dataset☆272Updated 5 years ago
- Grapheme to phoneme conversion with deep learning.☆358Updated 11 months ago
- ☆251Updated last year
- This is now the official location of the Merlin project.☆1,308Updated 4 years ago
- Simple text to phones converter for multiple languages☆1,232Updated last month
- This is a list of features, scripts, blogs and resources for better using Kaldi ( http://kaldi-asr.org/ )☆532Updated 2 years ago
- Some simple wrappers around kaldi-asr intended to make using kaldi's (online) decoders as convenient as possible.☆170Updated 3 years ago
- Allosaurus is a pretrained universal phone recognizer for more than 2000 languages☆565Updated 6 months ago
- FastCGI support for Kaldi ASR☆184Updated 5 years ago
- How to create your own model for vosk☆64Updated 3 years ago
- An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.☆830Updated last year
- Tacotron 2 - PyTorch implementation with faster-than-realtime inference modified to enable cross lingual voice cloning.☆358Updated last year
- Library to build speech synthesis systems designed for easy and fast prototyping.☆393Updated 4 months ago