[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny 300M model!
☆97Mar 4, 2026Updated 2 weeks ago
Alternatives and similar repositories for GPA
Users that are interested in GPA are comparing it to the libraries listed below
Sorting:
- Plug-and-play streaming semantic VAD for real-time full-duplex spoken dialogue systems.☆124Updated this week
- ☆29Jul 4, 2025Updated 8 months ago
- A large-scale speech corpus introduced in Spark-TTS, built from diverse open-source datasets for training text-to-speech (TTS) systems.☆108May 5, 2025Updated 10 months ago
- MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols☆18Nov 19, 2025Updated 4 months ago
- ☆100Jan 19, 2026Updated 2 months ago
- Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications☆89Dec 20, 2024Updated last year
- LEMAS‑TTS is a multilingual zero‑shot text‑to‑speech system, supporting 10 languages: Chinese English Spanish Russian French German Ital…☆92Jan 14, 2026Updated 2 months ago
- Trainging, inference, and testing of the SAC speech codec model.☆100Nov 1, 2025Updated 4 months ago
- A simple implementation for improving CosyVoice2 by GRPO method☆34Oct 17, 2025Updated 5 months ago
- ☆12Nov 7, 2024Updated last year
- Implementation of Acoustic BPE (Shen et al., 2024), extended for RVQ-based Neural Audio Codecs☆76Dec 3, 2025Updated 3 months ago
- Code for "StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model", AAAI2026 Oral☆46Jan 16, 2026Updated 2 months ago
- This repository implement a novel zero-shot TTS framework, named Flamed-TTS, focusing on the efficient generation and dynamic pacing in …☆57Aug 9, 2025Updated 7 months ago
- PyTorch Implementation of Multi-Singer (ACM-MM'21)☆139May 8, 2022Updated 3 years ago
- This repository contains a series of works on diffusion-based speech tokenizers, including the official implementation of the paper: "TaD…☆197Jan 25, 2026Updated last month
- An instruct text-to-speech solution based on LLaSA and CosyVoice2 developed by the ASLP lab and collaborators.☆227Feb 26, 2026Updated 3 weeks ago
- Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control☆102Feb 18, 2026Updated last month
- Torch Audio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆61Sep 5, 2025Updated 6 months ago
- Codebase for 'Scaling Rich Style-Prompted Text-to-Speech Datasets'☆156Mar 24, 2025Updated 11 months ago
- Open-Source Turn-Taking Detection Model and Dataset for Full-Duplex Spoken Dialogue Systems☆90Jan 25, 2026Updated last month
- [EMNLP 2025 Findings] Official code for EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion☆36Sep 9, 2025Updated 6 months ago
- ☆36Jan 6, 2026Updated 2 months ago
- ☆12Mar 11, 2025Updated last year
- Official repo for CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations☆64Jan 16, 2025Updated last year
- Variable Bitrate Residual Vector Quantization for Audio Coding☆50May 1, 2025Updated 10 months ago
- semantic tokenizer for speech and music☆21Jul 6, 2025Updated 8 months ago
- WaveNet implementation using tf.estimator☆21Jul 6, 2023Updated 2 years ago
- Code and data recipes for the paper: Optimal Condition Training for Target Source Separation by Efthymios Tzinis, Gordon Wichern, Paris S…☆14Feb 15, 2023Updated 3 years ago
- Sound Separation, Omni modal☆28Sep 15, 2025Updated 6 months ago
- faster inference☆28Jan 20, 2025Updated last year
- Digital Audio Effects in Python (material for MUSI6202@Georgiatech)☆15Nov 30, 2014Updated 11 years ago
- The baselines of ARC-Challenge-Interspeech2026☆57Dec 1, 2025Updated 3 months ago
- X-Talk is an open-source full-duplex cascaded spoken dialogue system framework enabling low-latency, interruptible, and human-like speech…☆187Updated this week
- ArtSpeech: Adaptive Text-to-Speech Synthesis with Articulatory Representations☆21Sep 21, 2025Updated 5 months ago
- Official implementation of WildFX Dataset Generating pipeline.☆15Oct 21, 2025Updated 5 months ago
- ☆36Sep 6, 2025Updated 6 months ago
- Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.☆80Jan 14, 2026Updated 2 months ago
- [ACL 2025] OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching☆45Feb 9, 2025Updated last year
- Python Wrapper of Silero VAD☆64May 8, 2025Updated 10 months ago