analiza aiqbench
Kyutai's Voice of Reason demonstrates that speech-native architectures can achieve competitive math reasoning accuracy (77.1%) without intermediate transcription or text LLMs, validating a direct audio-to-audio approach for spoken mathematics. While cascaded pipelines currently retain an edge in pure reasoning capability, this model proves that eliminating latency-heavy conversion stages is feasible through advanced reinforcement learning techniques on standard hardware like a single H100.
Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning
Kyutai has released Voice of Reason, 2 open-weight speech-to-speech models built on GLM-4-Voice-9B. Supervised fine-tuning and reinforcement learning lift spoken GSM8K accuracy from 27.3% to 77.1%. There is no transcription step and no text LLM in the loop. Both checkpoints are on Hugging Face and run on a single H100. The post Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning appeared first on MarkTechPost.
Kyutai has released Voice of Reason, 2 open-weight speech-to-speech models that solve math problems out loud. Both start from GLM-4-Voice-9B and add supervised fine-tuning (SFT) and reinforcement learning (RL). There is no transcription step and no separate text LLM in the loop. On spoken GSM8K, accuracy climbs from 27.3% for the base model to 77.1%. Is it deployable? Yes, for self-hosting. Kyutai ran both BF16 checkpoints on a single H100. You also need the GLM-4-Voice repo for…
Extras afișat conform termenilor RSS ai publicației · 77 cuvinte · textul integral și figurile sunt pe site-ul publicației
Subiecte conexe
Best Open Speech Recognition (ASR) Models in 2026: WER, Languages, Latency, and License Compared
MarkTechPost · 23 iul. 2026
[AINews] not much happened today
Latent Space · 10 sept. 2026
[AINews] Muse Spark 1.3 matches GPT-5.6-Sol, confirming Meta Superintelligence as the newest Frontier Lab, >90% discount for training
Latent Space · 3 sept. 2026
[AINews] Claude Fable/Mythos 5.1: new SOTA model, 75% cache price cut but 70% more output tokens
Latent Space · 2 sept. 2026