PaddleSpeech Releases
63 releases of PaddlePaddle/PaddleSpeech
- 1.4.2
A bug fix release addressing startup issues, login placeholder problems, and updates to various translations.
Jan 21, 2024
- 1.4.0
A major feature release introducing support for multiple Dockge instances, allowing users to manage and proxy multiple Docker stacks from a single interface.
Jan 3, 2024
- 1.3.4
A minor release focusing on UI improvements and bug fixes related to YAML processing and Docker Compose plugin updates.
Dec 16, 2023
- r1.4.1PaddleSpeech r1.4.1
Minor bug fix release addressing typeguard version compatibility issue.
Apr 14, 2023
- r1.4.0PaddleSpeech r1.4.0
Major TTS improvements with Cantonese TTS support across multiple inference backends, VITS inference pipeline, and new ASR capabilities including code-switch recognition.
Mar 15, 2023
- r1.3.0PaddleSpeech r1.3.0
Major release adding U2/U2++ Conformer support with C++ deployment, Whisper and Wav2vec2 models, and end-to-end prosody prediction for TTS.
Dec 14, 2022
- r1.2.0PaddleSpeech r1.2.0
A significant update introducing VITS voice cloning, ERNIE-SAT synthesis, BiTransformer decoders, and various TTS/ASR fixes.
Oct 10, 2022
- r1.1.0PaddleSpeech r1.1.0
A major overhaul introducing VITS models, ONNX support for TTS, SpeechX refactoring, and a new speech web demo.
Aug 19, 2022
- r1.0.0PaddleSpeech r1.0.0
The initial stable release (v1.0) of PaddleSpeech, introducing industrial-grade Streaming ASR (PP-ASR), Streaming TTS (PP-TTS), and Voiceprint Recognition (PP-VPR).
May 13, 2022
- r1.0.0aPaddleSpeech r1.0.0a
The alpha release leading up to v1.0.0, establishing core streaming ASR/TTS infrastructure, WebSocket support, and speaker verification features.
Apr 28, 2022
- r0.2.0PaddleSpeech r0.2.0
This release introduces significant updates across speech-to-text, text-to-speech, and audio processing modules, including online CTC decoding, new vocoders like WaveRNN and HiFiGAN, and a new server framework.
Apr 1, 2022
- r0.1.2PaddleSpeech r0.1.2
Minimal release notes: "### Bug Fix: 1. FIxed the version of librosa==0.8.1. Solve the compatibility issue caused by librosa upgrading. #1426"
Feb 25, 2022
- v1.4.1
Jan 22, 2022
- r0.1.1PaddleSpeech r0.1.1
A minor update focusing on CLI improvements, the addition of four ASR decoding methods, and refinements to TTS models including speaker embedding support.
Jan 14, 2022
- v1.4.0
Jan 2, 2022
- v1.3.4
Dec 29, 2021
- r0.1.0PaddleSpeech r0.1.0
The initial release of PaddleSpeech, establishing a unified platform for speech tasks including ASR, TTS, Speech Translation, and Audio Classification with a robust CLI.
Dec 23, 2021
- v1.3.3
Nov 23, 2021
- v2.1.1DeepSpeech v2.1.1
A DeepSpeech-focused release that adds alignment utilities, refactors the data pipeline, introduces an online model, and expands dataset support.
Aug 16, 2021
- v1.3.2
Aug 15, 2021