freds0 / katube
KATube is a tool to automate the process of creating datasets for training Text-To-Speech (TTS) and Speech-To-Text (STT) models. From a list of YouTube playlists or YouTube channels, KATube will generate dataset with audios and texts.
☆22Updated 6 months ago
Alternatives and similar repositories for katube:
Users that are interested in katube are comparing it to the libraries listed below
- NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment☆16Updated 2 years ago
- Prosodic Speech Segmentation with Transformers☆25Updated 11 months ago
- Convert English text from written expressions into spoken forms☆24Updated 2 years ago
- Generate audio datasets for training Text-To-Speech models, through smart audio splitting with silence detection, and transcription using…☆28Updated last year
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated last year
- ☆12Updated 3 weeks ago
- PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS☆22Updated 3 years ago
- CML-TTS: A Multilingual Dataset for Speech Synthesis☆29Updated 6 months ago
- Collection of scripts from mHuBERT-147.☆24Updated 3 months ago
- This repository contains all the code necessary for running the multilingual distilwhisper from Ferraz et al. 2024 IEEE ICASSP paper.☆20Updated 11 months ago
- ☆26Updated 11 months ago
- ☆56Updated 2 years ago
- SpeechGLUE is a speech version of the GLUE benchmark, driven by text-to-speech.☆13Updated last year
- A handy dataset of noises for ASR☆19Updated 5 years ago
- ☆12Updated 6 months ago
- [IJCAI'23] Learning to Speak from Text for Low-Resource TTS☆63Updated last year
- GPT for FACodec☆13Updated 10 months ago
- Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark☆25Updated 7 months ago
- Zero-Shot Foreign Accent Conversion without a Native Reference☆29Updated 9 months ago
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆47Updated last year
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one☆27Updated 6 months ago
- NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates [WIP]☆24Updated 2 years ago
- 56 language, 1 model Multilingual ASR☆25Updated 3 years ago
- Finally, some decent sample sentences☆22Updated last year
- Adaptive Vocoder for Custom Voice☆59Updated 2 years ago
- ☆41Updated last year
- End-to-End SpeechSynthesis system with fastspeech2 & hifigan☆13Updated 2 years ago
- ☆36Updated 5 months ago
- Just another FastSpeech 2 but cleaner code :)☆26Updated 7 months ago
- asr2k☆49Updated 8 months ago