fakerybakery / OpenF5-TTSLinks
(WIP) A retrain of F5-TTS on permissively-licensed data
☆11Updated last month
Alternatives and similar repositories for OpenF5-TTS
Users that are interested in OpenF5-TTS are comparing it to the libraries listed below
Sorting:
- StyleTTS 2 Optimized Training Fork☆29Updated 4 months ago
- High quality text-to-speech based on StyleTTS 2.☆47Updated this week
- StyleTTS2 + Vocos as a Decoder☆12Updated 2 months ago
- ☆13Updated 9 months ago
- Llasa Speed Up☆29Updated this week
- Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark☆27Updated 3 weeks ago
- Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"☆38Updated this week
- Unofficial implementation of ConvNeXt-TTS powered by lightning☆17Updated 7 months ago
- A lightweight, efficient variation of the StyleTTS 2 text‐to‐speech model.☆18Updated last week
- ☆26Updated 3 months ago
- A TTS Trained on Universal Audio.☆22Updated this week
- [ACMMM'2024] Generative Expressive Conversational Speech Synthesis☆34Updated 7 months ago
- Zero-Shot Emotion Style Transfer☆45Updated last month
- Just another FastSpeech 2 but cleaner code :)☆26Updated 11 months ago
- PitchVC: Pitch Conditioned Any-to-Many Voice Conversion☆34Updated 11 months ago
- Multispeaker Community Vocoder Model for DiffSinger☆37Updated 3 weeks ago
- My vocoder experiments☆29Updated 7 months ago
- speaker-disentangled speech linguistic content quantizer☆16Updated 2 months ago
- Simple and lightweight Zero-shot Text-to-Speech (TTS) synthesis model☆24Updated last month
- ☆20Updated 7 months ago
- ☆35Updated last year
- An open-source Kazakh Emotional Text-to-Speech Dataset☆29Updated last year
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one☆27Updated 9 months ago
- Self-supervised Generative LM-based Voice Conversion☆36Updated last month
- A collection of all our phonemeizers for dataset construction and inference☆23Updated 3 months ago
- Try to replicate the architecture of MiniMaxTTS mentioned in it's technical report☆31Updated 2 weeks ago
- AudioSR-Upsampling (any -> 48kHz)☆41Updated last year
- Torchaudio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆11Updated 5 months ago
- ☆18Updated last year
- ☆10Updated 6 months ago