Antalia-2 Mini: A 7.6-million-parameter Turkish text-to-speech model trained entirely on synthetic speech
cs.CL, cs.SD
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/cmusphinx/cmudict
Terminology
Sources
- The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speech
- Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models
- Classifier-Free Diffusion Guidance
- SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System
- Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model
- Improved Training Technique for Shortcut Models
- FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech Synthesis
- FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
- Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech
- GLU Variants Improve Transformer
- Staged Depth-Pruning Distillation of a Flow-Matching Text-to-Speech Teacher: A Compact Hindi Speech Synthesizer
- Qwen3 Technical Report
- Training Text-to-Speech Model with Purely Synthetic Data: Feasibility, Sensitivity, and Generalization Capability
- VoxCPM2 Technical Report
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data