ML Research Wiki / Benchmarks / Speech Synthesis / LibriTTS

LibriTTS

Speech Synthesis Benchmark

Performance Over Time

📊 Showing 15 results | 📏 Metric: PESQ

Top Performing Models

Rank Model Paper PESQ Date Code
1 PeriodWave-Turbo-L Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization 4.45 2024-08-15 📦 sh-lee-prml/periodwave
2 BigVGAN-v2 📚 BigVGAN: A Universal Neural Vocoder with Large-Scale Training 4.36 2022-06-09 📦 IAHispano/Applio 📦 sh-lee-prml/hierspeechpp 📦 nvidia/bigvgan 📦 sh-lee-prml/periodwave 📦 sh-lee-prml/BigVGAN
3 EVA-GAN-big 📚 EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks 4.35 2024-01-31 📦 fishaudio/vocoder
4 PeriodWave + FreeU PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation 4.25 2024-08-14 📦 sh-lee-prml/periodwave
5 RFWave RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction 4.23 2024-03-08 📦 bfs18/rfwave
6 BigVSAN (w/ snakebeta) BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network 4.12 2023-09-06 📦 IAHispano/Applio 📦 sony/bigvsan 📦 sony/bigvsan_eval
7 BigVSAN BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network 4.12 2023-09-06 📦 IAHispano/Applio 📦 sony/bigvsan 📦 sony/bigvsan_eval
8 EVA-GAN-base 📚 EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks 4.03 2024-01-31 📦 fishaudio/vocoder
9 BigVGAN BigVGAN: A Universal Neural Vocoder with Large-Scale Training 4.03 2022-06-09 📦 IAHispano/Applio 📦 sh-lee-prml/hierspeechpp 📦 nvidia/bigvgan 📦 sh-lee-prml/periodwave 📦 sh-lee-prml/BigVGAN
10 Vocos Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis 3.70 2023-06-01 📦 collabora/whisperspeech 📦 whisperspeech/whisperspeech 📦 IAHispano/Applio 📦 gemelo-ai/vocos

All Papers (15)