sarulab-speech / UTMOS22
UT-Sarulab MOS prediction system using SSL models
☆208Updated 10 months ago
Alternatives and similar repositories for UTMOS22:
Users that are interested in UTMOS22 are comparing it to the libraries listed below
- Reference-aware automatic speech evaluation toolkit☆142Updated 2 months ago
- Easy-to-Use Speech MOS predictors☆264Updated last year
- Versatile Evaluation of Speech and Audio☆157Updated this week
- UTokyo-SaruLab MOS Prediction System☆147Updated 2 months ago
- FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3☆187Updated 10 months ago
- It's a repository for implementations of neural speech editing algorithms.☆193Updated last year
- Unofficial implementation of miipher☆119Updated 10 months ago
- ☆88Updated last year
- Audio Codec Speech processing Universal PERformance Benchmark☆238Updated 3 months ago
- An official implementation of "UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data"☆133Updated last year
- Layer-wise analysis of self-supervised pre-trained speech representations☆100Updated 4 months ago
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆189Updated 5 months ago
- ☆168Updated 2 years ago
- Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion (Interspeech 2022)☆114Updated last year
- Unofficial pytorch implementation of BigVGAN: A Universal Neural Vocoder with Large-Scale Training☆134Updated 2 years ago
- ☆115Updated 2 years ago
- Fre-GAN: Adversarial Frequency-consistent Audio Synthesis☆102Updated 3 years ago
- This is the implementation for "ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Rhythm"☆130Updated last year
- Models and code for RepCodec: A Speech Representation Codec for Speech Tokenization☆168Updated 7 months ago
- MOS score prediction by fine-tuned wav2vec2.0 model☆151Updated 2 years ago
- HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement☆155Updated 2 years ago
- High-Fidelity Neural Phonetic Posteriorgrams☆104Updated 3 months ago
- LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning☆120Updated 8 months ago
- A sequence-to-sequence voice conversion toolkit.☆93Updated 7 months ago
- An implementation of Microsoft's "AdaSpeech: Adaptive Text to Speech for Custom Voice"☆96Updated 2 years ago
- Alignment files of LibriTTS.☆61Updated 4 years ago
- Official implementation of the source-filter HiFiGAN vocoder☆246Updated last year
- Evaluation and Benchmarking of Speech Super-resolution Methods☆146Updated 2 years ago
- [AAAI 2024] Code for CTX-vec2wav in UniCATS☆128Updated 8 months ago
- Official implementation for the paper Fine-grained style control in transformer-based text-to-speech synthesis.☆88Updated 2 years ago