freds0 / kabooks
KABooks is a tool to automate the process of creating datasets for training Text-To-Speech (TTS) and Speech-To-Text (STT) models. Using audiobooks, KABooks will generate dataset with segmented audios and aligned texts.
☆12Updated 2 years ago
Alternatives and similar repositories for kabooks
Users that are interested in kabooks are comparing it to the libraries listed below
Sorting:
- Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks☆17Updated last year
- ☆14Updated last year
- NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment☆16Updated 3 years ago
- ☆11Updated 2 months ago
- ☆10Updated last year
- ☆11Updated 2 years ago
- ☆13Updated 8 months ago
- Conditional Variational Auto-Encoder with Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech☆22Updated 2 years ago
- speaker-disentangled speech linguistic content quantizer☆14Updated last month
- A Benchmark Corpus for Low-Resource Cantonese Punctuation Restoration from Speech Transcripts☆15Updated 5 months ago
- Aty-TTS: Improving fairness for spoken language understanding in atypical speech with Text-to-Speech☆10Updated this week
- A unified model for zero-shot singing voice conversion and synthesis☆22Updated 2 years ago
- Code for the winning solution in the SE&R 2022 Challenge - SER track.☆14Updated 2 years ago
- 'Grad-TTS' with Multilingual Cleaners☆10Updated last year
- Grapheme-to-phoneme (G2P) conversion is the process of generating pronunciation for words based on their written form. It has a highly es…☆19Updated 3 years ago
- A handy dataset of noises for ASR☆21Updated 5 years ago
- LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM☆16Updated last year
- ☆10Updated 6 months ago
- ☆20Updated last year
- Hifi-like Vocoder implemented in PyTorch☆13Updated 2 years ago
- ☆12Updated 2 years ago
- SpeechGLUE is a speech version of the GLUE benchmark, driven by text-to-speech.☆13Updated last year
- A collection of all our phonemeizers for dataset construction and inference☆22Updated 2 months ago
- NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates [WIP]☆24Updated 2 years ago
- text to speech☆10Updated last year
- End-to-End SpeechSynthesis system with fastspeech2 & hifigan☆13Updated 2 years ago
- Accompanying repository for the paper "DiffVox: A Differentiable Model for Capturing and Analysing Professional Effects Distributions"☆18Updated this week
- Forced alignment decoder for Whisper.☆14Updated last year
- SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech☆11Updated last year
- 60k hours of phoneme-aligned audio from audio books☆18Updated 9 months ago