Cactus Compute released Whistle, a 16.9 MB on-device speech recognition model that runs on CPU with no dependencies and loads into the same C++ engine as Needle. Whistle handles transcription in seven…
NVIDIA published a fine-tuning workflow for its Nemotron 3.5 ASR streaming 0.6B model that adapts the 40-language-locale speech recognizer to Saudi Najdi and Hijazi dialects using the NeMo framework, …
Researchers released BuzzASR, a collection of 102 language-specialized fine-tuned Whisper models for automatic speech recognition, according to an arXiv paper (2609.09554v1). BuzzASR models outperform…
Microsoft released MAI-Transcribe-2 on September 3rd, a speech-to-text model priced at $0.10 per audio hour, claiming a 5.2% average word error rate on the FLEURS benchmark across 60 languages and pro…
Microsoft AI released MAI-Transcribe-2 on September 3 at $0.10 per audio hour, claiming it is 72% cheaper than OpenAI's GPT-Transcribe and 10x faster in non-streaming tests, with a 5.2% average word e…
Meta released Muse Voice Transcribe on September 1, 2026, and Microsoft released MAI-Transcribe-2 on September 3, 2026, with Meta reporting first place on the Artificial Analysis streaming STT ranking…
Google introduced Gemini 3.5 Transcribe, its most precise speech-to-text model, available via the Gemini API in Google AI Studio and Gemini Enterprise Agent Platform. The model achieves a 4.0% word er…
A new automatic speech recognition model, Diffusion-gemma-asr, achieves 15x faster inference than OpenAI's Whisper by freezing a Whisper-small encoder and DiffusionGemma weights and adding a 42M param…
Interfaze, a research lab, released diffusion-gemma-asr, the first open-source diffusion ASR audio model that is 15x faster than OpenAI's Whisper. The model achieves a 6.6% word error rate on Librispe…
A new study from arXiv shows that multilingual encoder initialization benefits streaming automatic speech recognition (ASR) only at low target-language data scales, with the advantage decaying as data…