Argmax Pro SDK 3 Brings Qwen3-ASR to iOS with Word-Level Timestamps
solyarisoftware · x · 2026-08-01
Argmax released Pro SDK 3, successfully deploying the Qwen3-ASR-1.7b speech recognition model on iOS devices, enabling real-time transcription and custom vocabulary within 2GB of memory.
Developers also discovered that Qwen3-ASR can natively generate word-level timestamps without relying on an additional forced alignment model, drastically saving disk and memory overhead for on-device deployment.
More from Models
- 1-bit Quantization Shrinks Kimi K3 by 62% While Retaining 1M Context — rohanpaul_ai · 2026-08-01
- 1-bit Kimi K3 Quant Tested: 2.8T Model Compressed to 590GB Runs Locally — rohanpaul_ai · 2026-08-01
- Open Source Miniaturization: Opus-Level Models on Laptops Next Year? — No-Meringue5867 · 2026-08-01
- Testing DeepSeek v4 Flash: Major Improvements in UI/UX Design — curiousily_ · 2026-08-01
- Inkling-Small Local Test: Accurately Parses 85-Cell Medical Lab Reports on Mac — MaziyarPanahi · 2026-08-01
- Surge AI Releases High-Quality Datasets: Non-Coding Data Boosts Coding Benchmarks — echen · 2026-08-01