festvox / speech_tools
Edinburgh Speech Tools
☆59Updated last year
Alternatives and similar repositories for speech_tools:
Users that are interested in speech_tools are comparing it to the libraries listed below
- Festvox voice building tools☆99Updated 10 months ago
- Frontend system for HMM-based speech synthesis models generated by HTS.☆40Updated 4 years ago
- Labeled data for homograph disambiguation☆57Updated last year
- C++ Implementation of the Information Bottleneck System☆23Updated 6 years ago
- BurrMill core☆21Updated 3 years ago
- Autoregressive HMM version of the HTS demo for statistical speech synthesis (includes autoregressive clustering)☆16Updated 10 years ago
- Official home of the Idlak Speech Synthesis Toolkit☆66Updated 3 years ago
- A JAX library for building lattice-based speech transducer models☆45Updated 3 months ago
- Prosodic Speech Segmentation with Transformers☆25Updated last year
- pytorch implementation of DNN-HSMM for TTS☆63Updated 4 years ago
- Collection of scripts and utilities for reorganizing corpora to use with the Montreal Forced Aligner☆44Updated 3 years ago
- Hybrid speech synthesiser☆28Updated 6 years ago
- A phoneme-allophone database for many languages☆52Updated 4 years ago
- Tools for working with the CMU Pronunciation Dictionary☆35Updated 7 years ago
- ☆22Updated 3 years ago
- A data annotation pipeline to generate high-quality, large-scale speech datasets with machine pre-labeling and fully manual auditing.☆102Updated 2 years ago
- Unicode Standard tokenization routines and orthography profile segmentation☆35Updated last month
- Grapheme to phoneme converter for Estonian☆13Updated 3 years ago
- Data and code for grapheme-to-phoneme transducers in lots of languages☆132Updated last year
- Adapt Kaldi-ASR nnet3 chain models from Zamia-Speech.org to a different language model☆33Updated 5 years ago
- Repository for the web pages and scripts associated with OpenSLR: the open speech and language repository☆25Updated 4 years ago
- ☆42Updated 3 years ago
- Word alignments generated by the Montreal Forced Aligner for the Librispeech dataset☆161Updated 6 years ago
- ☆40Updated 3 years ago
- Praaline is an open-source system to manage, annotate, visualise and analyse spoken language corpora☆28Updated 2 years ago
- An example directory for running Multi-Task Learning training on Kaldi neural networks. In Kaldi-speak, this is an egs dir for nnet3 trai…☆54Updated 5 years ago
- Read-only unofficial mirror of the OpenGrm NGram Library☆8Updated 5 years ago
- Phonetic and phonological vocoding platform☆16Updated 8 years ago
- ☆48Updated 4 years ago
- A "Crowd-Built" continuously growing speech dataset with transcripts. The dataset contains multiple languages and is intended for anyone …☆41Updated 2 years ago