replying to @dtinth-bot
Yes, please delete the old work trees and I already put in the environment variables in place of the placeholders.
Commit
19ec4af
Old worktrees deleted. Qwen3.8 works: draft PR 125. On the 9.2s clip, 3 runs: same transcript and tokens as 3.5-flash in 2 of 3 (1 rendered deploy in Thai), ~10s, coarser partials (9-11 vs 31). Handshake unchanged, needs workspace endpoint.
Caveats: no dated model id exists yet (I exempted it by name from the pinned-ids test), and price is a placeholder copied from 3.5-flash, docs give none. Want more recordings tried, or the real price from your console? @dtinth
- Please check the pricing https://www.alibabacloud.com/help/en/model-studio/model-pricing
- Please also make a PR
- Please send me an infographic about how it went
alibabacloud.comModel inference pricing - Alibaba CloudAlibaba Cloud Model Studio model pricing,Alibaba Cloud Model Studio:Model API calls are billed on a pay-as-you-go basis by default. NoteThis document only lists standard prices. For the latest promotions, visit the Model Studio console.
Pricing checked: 3.8 is $0.93 audio in, $0.23 text in, $0.70 text out per 1M, so ~4.4x cheaper per clip than 3.5-flash. PR 125 is up (draft) with real prices. Infographic attached. @dtinth
Side finding: our 3.5 price table charges $17.70 for text output, but the page lists $3.30 for text and $17.70 for audio. 3.5 costs may be 5x overstated on output. Left alone, want it fixed? @dtinth
- Please fix.
- Also, can you visualize the timing of the partials that arrive? Do they arrive after the spoken word is finished or do they arrive as I speak?
- There is yet another model Qwen-Audio-3.1-ASR. See https://arxiv.org/html/2610.28711v1
- Overview…
arxiv.orgQwen-Audio-3.1-ASR Technical Report
On it: fixing the 3.5 text-output rates, then a timeline of when partials arrive vs the audio, then the two Qwen-Audio-3.1 models. Will report back.
@dtinth Both Audio-3.1 models stream WHILE you speak (Omni does not). message final = perfect Thai, but its partials are junk; streaming final lacks spaces. Prices unverified (page truncated). Add as provider in #125?
Please add. BTW, can you show me the exact text that came out from the four models? We don't care about the partials. It is there to, you know, uh, help the user feel assured that they are being listened to.
@dtinth Added qwen-audio provider (both models), pushed to #125, 170 tests pass. Correction: message is not stable. 5 of 6 runs gave the good text; 1 wrote Thai phonetics for every English word. Streaming: no word spaces, MongoDB garbled every run. Prices still unverified, please…
Please shepherd the PR. https://github.com/dtinth/vxbeamer/actions/runs/43163769793/job/131000757108?pr=125
GitHubfeat(vxasr): add Qwen3.8 Omni and Qwen-Audio-3.1-ASR models · dtinth/vxbeamer@339696aself-hosted, personal speech transcriber with a real-time web interface - feat(vxasr): add Qwen3.8 Omni and Qwen-Audio-3.1-ASR models · dtinth/vxbeamer@339696a
@dtinth CI was my miss: with only the API key the backend listed 3.8 as selectable, then threw. Fixed so workspace-endpoint models need DASHSCOPE_WORKSPACE_ID to be offered, plus tests. All 4 checks green on 62211b6. PR #125 still draft.
Mark ready after an adversarial review, please.
@dtinth #125 is marked ready for review, all 4 checks green on 0541231. Still open for you: the Audio-3.1 prices and qwen3-omni-flash text rate are unverified. Not merged.
For pricing feel free to use agent browser
@dtinth Read the pricing page with agent-browser. Audio-3.1 message+streaming confirmed $0.93 in / $0.70 out. Fixed qwen3-omni-flash text out: $18.13 -> $3.67 (audio input, text only). Pushed 716ead6, checks green, PR still ready. Same-day reading, not merged.
Merged.
Please give me a list of new ASR configurations added by the PR so I can put it in env.
@dtinth New ids (all need DASHSCOPE_WORKSPACE_ID too): qwen-omni/qwen3.8-omni-flash-realtime, qwen-audio/qwen-audio-3.1-asr-flash-message, qwen-audio/qwen-audio-3.1-asr-flash-streaming. Append to ASR_CONFIGURATIONS, comma-separated.
This page: https://www.alibabacloud.com/help/en/model-studio/qwen-audio-3-1-asr-flash-message?spm=a2c63.p38356.help-menu-2400256.d_1_0_6_5_3.4f3658fdJY2001 says that the model supports native text polishing. How to turn it on and what is customizable with this model? You can make infograhic after playing around with its params.
alibabacloud.comqwen-audio-3.1-asr-flash-message - Alibaba Cloudqwen-audio-3.1-asr-flash-message Model Info,Alibaba Cloud Model Studio:Qwen-Audio-3.1-ASR-Flash-Message is a generative speech recognition model optimized for voice messages, voice input, and enterprise scenarios. It supports Chinese, English, and other languages, with o...
commit 19ec4af
From my preliminary usage, it tends to transcribe numbers, like spoken numbers, as words rather than as digits. It also tends to spell out English words in Thai when it is placed inside a Thai sentence.