https://www.anchorterminal.com/tools/qwen3-asr-1-7b Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3-ASR-1.7B. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/qwen3-asr-1-7b#rev_4015 https://www.anchorterminal.com/tools/qwen3-asr-1-7b#rev_4015 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen's most recent change was the -hf repository's template and README update for custom hotwords on 22 July 2026, after a dated README news line on 26 June marked the -hf builds' arrival. Nothing was replaced. Upkeep stops there. None of the 22 discussions that aren't pull requests has a Qwen reply, a Transformer version error report with 11 comments waits, and the qwen_asr code hasn't changed since 30 January. GitHub issues weren't counted. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-asr-1-7b#rev_4016 https://www.anchorterminal.com/tools/qwen3-asr-1-7b#rev_4016 Wed, 21 Oct 2026 00:00:00 +0000 review An 8 GB GPU covers it. Alibaba ships BF16 only, 4.09 GB in the -hf layout for Transformers and 4.70 GB in the original for vLLM and SGLang, and ggml-org's Q8_0 GGUF is 2.52 GB. The card states no memory figure and recommends FlashAttention 2. Apache 2.0, ungated, though neither Hub repository has a LICENSE file. DeepInfra is the only live provider, and Model Studio's Qwen3-ASR-Flash isn't documented as the same weights. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-asr-1-7b#rev_4017 https://www.anchorterminal.com/tools/qwen3-asr-1-7b#rev_4017 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3-ASR-1.7B takes context text in the system turn and a forced language by assistant prefill, both documented with the Jinja template that ships in each repository. The returned language and transcript fields come with parse_asr_output and a parsed return_format in Transformers. Timestamps go through Qwen3-ForcedAligner-0.6B, and streaming through vLLM only. On the Open ASR Leaderboard the -hf build records 5.4 English short-form WER, 6.56 multilingual and an RTFx of 819.3. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-asr-1-7b#rev_4018 https://www.anchorterminal.com/tools/qwen3-asr-1-7b#rev_4018 Wed, 21 Oct 2026 00:00:00 +0000 review Both shards of Qwen3-ASR-1.7B carry a SHA-256 on the Hub, and the safetensors load with runtime code and a shipped template, so nothing from the repository runs. The qwen-asr helper is Alibaba's PyPI package, outside the repository. The card's Docker example mounts the host's Docker socket without a warning, and nothing addresses instructions spoken into audio that an agent then reads. QwenLM/Qwen3-ASR has no SECURITY.md, and no safety results were found. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-asr-1-7b https://www.anchorterminal.com/tools/qwen3-asr-1-7b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3-ASR-1.7B is Alibaba's open-weight speech recognition model for 30 languages and 22 Chinese dialects, with language identification, context hints and streaming, published on Hugging Face in BF16 under Apache 2.0.