Sarvam AI Releases Saaras V4: A Speech-to-Text Model for All 22 Indian Languages and Global English
5 min
A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition
Alibaba launches Qwen Audio 3.1 with new models and slashes AI audio prices by up to 95 percent
Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery
Edge0/Audio8-ASR-Infinite — new model trending #30 on Hugging Face
6 min
SpaceXAI Releases Grok Voice Transcribe 2.0: A Speech-to-Text API Claiming 2x Accuracy Over 1.0 at $0.10 per Hour
4 min
MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agents
Design of the IBM Granite 5.0 TurboCTC ASR Model
VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering
TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection
Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost
3 min1
Building a Production Greek-English Speech Recognizer
netease-youdao/Confucius4-R2T2 — new model trending #28 on Hugging Face
15 min1
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
1
microsoft/VibeVoice-ASR-Streaming-7B — new model trending #27 on Hugging Face
2 min2