sarulab-speech / UTMOS22Links
UT-Sarulab MOS prediction system using SSL models
☆235Updated last year
Alternatives and similar repositories for UTMOS22
Users that are interested in UTMOS22 are comparing it to the libraries listed below
Sorting:
- Reference-aware automatic speech evaluation toolkit☆152Updated 5 months ago
- UTokyo-SaruLab MOS Prediction System☆185Updated this week
- Easy-to-Use Speech MOS predictors☆287Updated last year
- ☆98Updated last year
- FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3☆200Updated last year
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆194Updated 8 months ago
- Versatile Evaluation of Speech and Audio☆260Updated this week
- An official implementation of "UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data"☆135Updated last year
- MOS score prediction by fine-tuned wav2vec2.0 model☆158Updated 2 years ago
- It's a repository for implementations of neural speech editing algorithms.☆198Updated last year
- Layer-wise analysis of self-supervised pre-trained speech representations☆103Updated 7 months ago
- Training code for FAcodec presented in NaturalSpeech3☆209Updated 9 months ago
- Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion (Interspeech 2022)☆117Updated last year
- Unofficial implementation of miipher☆124Updated last year
- Models and code for RepCodec: A Speech Representation Codec for Speech Tokenization☆179Updated 10 months ago
- HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement☆157Updated 2 years ago
- Audio Codec Speech processing Universal PERformance Benchmark☆255Updated last month
- Fre-GAN: Adversarial Frequency-consistent Audio Synthesis☆105Updated 3 years ago
- ☆171Updated 2 years ago
- Unofficial pytorch implementation of BigVGAN: A Universal Neural Vocoder with Large-Scale Training☆134Updated 2 years ago
- An implementation of Microsoft's "AdaSpeech: Adaptive Text to Speech for Custom Voice"☆97Updated 2 years ago
- ☆117Updated 2 years ago
- Unofficial SoundStream implementation of Pytorch with training code and 16kHz pretrained checkpoint☆68Updated last year
- Official implementation of the source-filter HiFiGAN vocoder☆252Updated last year
- iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier Transform☆247Updated 2 years ago
- High-Fidelity Neural Phonetic Posteriorgrams☆112Updated 3 months ago
- A speaker embedding network in Pytorch that is very quick to set up and use for whatever purposes.☆88Updated last month
- Official Implement of Multi-Stage Multi-Codebook (MSMC) TTS☆164Updated last year
- Evaluation and Benchmarking of Speech Super-resolution Methods☆149Updated 2 years ago
- This is the implementation for "ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Rhythm"☆132Updated last year