Fish Audio S2 Technical Report research paper by Fish Audio, 2026

Fish Audio · Mar 9, 2026 · Foundation models · 17 citations · 40 upvotes · unverified

Fish Audio S2 is an open-source text-to-speech system with multi-speaker capabilities, multi-turn generation, and instruction-following control through natural-language descriptions, utilizing a multi-stage training approach and production-ready inference engine.

UnverifiedHugging Face's summary; not yet checked by hand.

Topic

Date	Paper	Lab	Citations
Oct 11, 2018	BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingPre-training a Transformer to fill in masked words, then fine-tuning it, beat task-specific models across language understanding tests.Google · Oct 2018Google	Google	121k
May 28, 2020	Language Models are Few-Shot LearnersGPT-3, a 175B-parameter model, does new tasks from a few examples in the prompt, with no fine-tuning.OpenAI · May 2020OpenAI	OpenAI	63.7k
Mar 15, 2023	GPT-4 Technical ReportA multimodal model that passes a simulated bar exam with a score around the top 10% of test takers.OpenAI · Mar 2023OpenAI	OpenAI	27.3k
Feb 27, 2023	LLaMA: Open and Efficient Foundation Language ModelsOpen models from 7B to 65B trained only on public data; the 13B model beats GPT-3 on most benchmarks.Meta · Feb 2023Meta	Meta	21.7k
Jul 31, 2024	The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Meta · Jul 2024Meta	Meta	18.9k
May 14, 2025	Qwen3 Technical ReportUnverifiedQwen3, a unified series of large language models, integrates thinking and non-thinking modes, reduces computational resources, and achieves state-of-the-art performance across various tasks and languages.Alibaba (Qwen) · May 2025 · UnverifiedAlibaba (Qwen)	Alibaba (Qwen)	8,100

About this paper

Authors: Shijia Liao, Yuxuan Wang, Songting Liu and 11 more
arXiv: 2603.08823 · PDF
Venue: arXiv.org
Citations: 17, 3 influential · Semantic Scholar
Upvotes: 40 · Hugging Face
Code: github.com/fishaudio/fish-speech
Lab: Fish Audio · on Companies · on Rounds

Changes

Date	What changed
Sep 25, 2026	Influential citationsfirst count: 3Sep 25, 2026
Sep 25, 2026	Citationsfirst count: 17Sep 25, 2026
Sep 25, 2026	New paperFound by the weekly scan, unverifiedSep 25, 2026

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

What it shows

Other foundation models papers

Changes

New papers by email