playwright-cli Releases

PaddleSpeech r1.5.0 upgrades the framework from Paddle 2.5.1 to 3.0.0-beta, adapting over 80 models and fixing numerous compatibility issues. The release introduces new AudioTools support for DAC training and enhances hardware compatibility with GCU, NPU, and MLU.

Mar 5, 2025

This release introduces significant updates to Speech-to-Text (S2T) with new models like WavLM and HuBERT, and expands Speech-to-Singing (SVS) capabilities with examples for DiffSinger and HiFiGAN. It also includes enhancements to the StarGANv2 voice conversion model and adds XPU support for various TTS models.

Jun 27, 2024

Minimal release notes: "# Others - fix typeguard version. https://github.com/PaddlePaddle/PaddleSpeech/pull/3056 @yt605155624"

Apr 14, 2023

This release adds comprehensive Cantonese TTS support including inference pipelines and CLI tools, alongside the introduction of the VITS inference pipeline and diffusion module for DiffSinger. It also refactors the engine directory and removes deprecated Fluid APIs from the ASR components.

Mar 15, 2023

This release focuses on high-performance deployment by adding U2++ C++ streaming ASR and introducing major new models like Whisper and Wav2vec2 for speech recognition. For synthesis, it adds end-to-end prosody prediction and adversarial losses for mixed-language TTS.

Dec 14, 2022