silenterus / deepspeech-cleaner
Multi-Language Dataset Cleaner/Creator for Mozilla's DeepSpeech Framework
☆47Updated last year
Related projects: ⓘ
- Jupyter Notebooks for creating Speech datasets☆46Updated 5 years ago
- Running Mozilla's implementation of Baidu DeepSpeech on Google Colaboratory☆16Updated 5 years ago
- 🐸TTS recipes for different datasets☆84Updated 2 years ago
- An HTML interface for finetuning the sync map output from aeneas☆53Updated 2 years ago
- Command line tool to create corpora for Common Voice☆75Updated 3 months ago
- Linguistic processing for Common Voice☆50Updated 8 months ago
- Multispeaker & Emotional TTS based on Tacotron 2 and Waveglow☆128Updated 3 years ago
- Pytorch implementation of Deepmind's WaveRNN model☆120Updated 5 years ago
- Tool for creation, manipulation and maintenance of voice corpora☆80Updated 4 months ago
- A python library to generate speech dataset from Youtube videos☆35Updated 3 months ago
- Helsinki Prosody Corpus and A System for Predicting Prosodic Prominence from Text☆229Updated 4 years ago
- Python library for manipulating pronunciations using the International Phonetic Alphabet (IPA)☆78Updated 10 months ago
- speaker diarization system using an LSTM☆49Updated last year
- A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.☆13Updated 4 years ago
- SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model☆106Updated 3 years ago
- This is a legacy repo. Dev occurs now on GitHub.☆11Updated 3 years ago
- pronunciation dictionaries for multiple languages☆83Updated 7 years ago
- An easy way to fine-tune Wav2Vec 2.0 for low-resource languages.☆81Updated last year
- SailAlign is an open-source software toolkit for robust long speech-text alignment implementing an adaptive, iterative speech recognition…☆97Updated 2 years ago
- [deprecated] Pretrained models for pyannote-audio 1.x☆70Updated 2 years ago
- Forced Alignments for Common Voice☆29Updated 3 years ago
- Wav2vec resources and models for Brazilian Portuguese☆31Updated 2 years ago
- These are Jupyter Notebooks to help guide people to learn how to use Praat-Parselmouth☆36Updated 2 years ago
- Multilingual Grapheme to Phoneme☆47Updated 8 years ago
- Grapheme To Phoneme☆69Updated last month
- A tokenizer, text cleaner, and phonemizer for many human languages.☆272Updated 2 months ago
- Python module to clean and transliterate (i.e. normalize) German text including abbreviations, numbers, timestamps etc. It can be used to…☆29Updated 3 years ago
- A crash course for training speech recognition models using DeepSpeech.☆23Updated 3 years ago
- VCTK multi-speaker tacotron for ICASSP 2020☆265Updated 2 years ago
- ☆75Updated 3 months ago