FreedomIntelligence / S2S-ArenaLinks
☆16Updated last month
Alternatives and similar repositories for S2S-Arena
Users that are interested in S2S-Arena are comparing it to the libraries listed below
Sorting:
- This repository contains prompts & best practices to annotate audio clips with a very high degree of details using Audio-Language-Models☆34Updated 8 months ago
- WavReward: Spoken Dialogue Models With Generalist Reward Evaluators☆40Updated last month
- [ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer☆58Updated 7 months ago
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆73Updated 7 months ago
- ☆13Updated 9 months ago
- Using Pre-trained SSL Transformer Models for Speaker Verification☆9Updated 9 months ago
- Streaming Vocos☆27Updated 2 weeks ago
- ☆75Updated 3 weeks ago
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆59Updated 7 months ago
- ☆35Updated last year
- ☆19Updated last year
- Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.☆45Updated 3 weeks ago
- An automatic prosodic boundary annotation tool for Text-to-Speech Synthesis (TTS).☆48Updated last year
- Official release of StyleTalk dataset.☆67Updated 11 months ago
- [NeurIPS 2024] SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words☆50Updated last year
- The open source code for LLM-Codec☆135Updated 10 months ago
- Official code for "EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting"☆46Updated last month
- A large-scale speech corpus introduced in Spark-TTS, built from diverse open-source datasets for training text-to-speech (TTS) systems.☆76Updated last month
- Audio-FLAN☆157Updated 3 months ago
- Training code for MaskGCT-T2S model.☆20Updated 6 months ago
- ☆33Updated 11 months ago
- Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis☆27Updated 3 months ago
- BLSP-Emo: Towards Empathetic Large Speech-Language Models☆46Updated last year
- FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis (Accepted by ISCSLP'2024)☆25Updated last year
- We introduce the LLAMA1 Test Set, a comprehensive open-domain world knowledge QA dataset for evaluating question-answering systems. We pr…☆19Updated last year
- ☆50Updated 2 months ago
- Survey on speech generation work.☆20Updated last year
- The TTSDS benchmark evaluates synthetic speech quality by considering prosody, speaker identity, and intelligibility, comparing these fac…☆37Updated last week
- Official implementation for Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning☆93Updated 7 months ago
- ☆31Updated 3 months ago