156MB Phonon-2.5 Beats Whisper large-v3 on Multilingual ASR at 1/20th the Size
julianweisser · x · 2026-10-24
Fermion released Phonon-2.5, an open-weights (CC-BY-4.0) multilingual ASR model that pushes a new accuracy-to-size Pareto frontier.
- Just 156MB, yet it averages 11.71 WER on FLEURS across 25 languages, beating OpenAI's Whisper large-v3 (12.18) despite being 20x smaller, and edging out Parakeet Ultra (11.14 at 1.26GB) and Omnilingual LLM-1B (11.28 at 9.1GB)
- Claims to transcribe an hour of multilingual audio in 20 seconds on a MacBook Air
More from Models
- Moonshot Launches Kimi K3.1 Pro: 2.8T-Param Open-Weight Model Rivals GPT-6 and Opus 5.5 — Kimi_Moonshot · 2026-10-24
- Anthropic secretly A/B tests Claude limits: same $200 plan, ~20% less usage — RexDouglass · 2026-10-24
- Kimi K3.1 Pro Benchmarks: Tops SWE Marathon at 51.7, Near Opus 5.5 Across Coding Boards — scaling01 · 2026-10-24
- Kimi 3.1 priced at $2/$10 per 1M tokens, still not competitive vs DeepSeek, says investor — bindureddy · 2026-10-24
- NVIDIA's Nemotron 3.5 Bolt lands on Ollama: small VLM with 128K context — ollama · 2026-10-24
- LlamaIndex's OCRia-1 matches top parsers at 1/4 the cost, 7x faster than Claude — llama_index · 2026-10-24