QwenPaw Releases
145 releases of agentscope-ai/QwenPaw
- v3.1.4
Oct 5, 2025
- 25.9.0Release 25.9.0
Adds hardware and software support to NeMo Retriever extraction, including new GPU support (RTX Pro 6000, DGX B200), new OCR and VLM models, custom vector database implementations, and custom Lambda stages.
Sep 17, 2025
- v3.8.3
Minimal release notes: "More TypeScript-related fixes! Sorry for any hassle in the last couple of releases. **Full Changelog**: https://githu"
Aug 27, 2025
- v3.8.2
Minimal release notes: "**Full Changelog**: https://github.com/sampotts/plyr/compare/v3.8.1...v3.8.2"
Aug 27, 2025
- v3.8.1
Minimal release notes: "**Full Changelog**: https://github.com/sampotts/plyr/compare/v3.8.0...v3.8.1"
Aug 27, 2025
- v3.8.0
A Plyr video player library release that includes new Babel/Rollup plugins, fixes polyfill.io recommendation, adds Mux as a demo example, improves captioning and thumbnail CORS support, and updates PIP support.
Aug 27, 2025
- 25.6.3
A patched release to update the client's dependency on pypdfium2 to the latest stable version (v4.30.1) after the previous version was yanked from PyPI.
Jul 22, 2025
- v3.1.3
May 28, 2025
- v3.1.2
Apr 15, 2025
- v3.1.1
Mar 30, 2025
- r1.5.0PaddleSpeech r1.5.0
This release marks a major upgrade to PaddleSpeech by moving from Paddle 2.5.1 to Paddle 3.0.0-beta, requiring extensive adaptation of 80+ existing models to ensure functionality and accuracy. It introduces support for the AudioTools toolkit used in DAC (Descript-Audio-Codec) training and adds hardware backends for GCU, NPU, and MLU.
Mar 5, 2025
- r1.4.2PaddleSpeech r1.4.2
Adds WavLM and HuBERT ASR models, Squeezeformer architecture, and SVS examples using DiffSinger and HiFiGAN. Includes StarGANv2-VC enhancements and XPU support.
Jun 27, 2024
- 3.2.1Human Release v3.2
Upgrades development toolkits to latest versions and refreshes the Custom CI platform.
Feb 15, 2024
- 3.1.2Human Release v3.1
Major toolkit upgrade to Node.js v20 and TypeScript 5.1, including electron environment detection and various bug fixes.
Sep 18, 2023
- r1.4.1PaddleSpeech r1.4.1
Minimal release notes: "# Others - fix typeguard version. https://github.com/PaddlePaddle/PaddleSpeech/pull/3056 @yt605155624"
Apr 14, 2023
- r1.4.0PaddleSpeech r1.4.0
Introduces wav2vec2-zh finetune pipeline, Whisper support, and Cantonese TTS capabilities. Includes engine refactoring and VITS inference pipeline.
Mar 15, 2023
- r1.3.0PaddleSpeech r1.3.0
Adds U2/U2++ Conformer dy2static, Wav2vec2ASR, and Whisper CLI/Demos. Features streaming TTS FastDeploy and end-to-end prosody prediction.
Dec 14, 2022
- 3.0.1Human Release v3.0
Introduces high-resolution optimizations, enhanced device capabilities detection, and auto backend selection. Adds draw label templates and webgpu support.
Nov 22, 2022
- 2.11.1Human Release v2.11
Adds new webcam and video methods, redesigns segmentation handling, and introduces the RVM model for real-time body segmentation.
Oct 13, 2022
- 2.10.1Human Release v2.10
Updates to TFJS 3.20.0 and TypeScript 4.8, switches default backend to webgl, and adds InsightFace model support.
Sep 7, 2022