modelscope / modelscope/FunASR
增加Hotwords會造成語句變短及亂取代其他文字
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 20.4k
- Forks
- 2k
- Avg merge
- 4h 55m
- Merged PRs (30d)
- 169
Description
當我在realtime_ws.py執行時遇到兩個問題:
-
持續講話會在partial內容看到文字都有出現在預覽中, 但最後確定字串傳送到前端後會少掉一大部分的文字
比如原本看到預覽中顯示"为了更加高效率解决您遇到的问题，请按照模板提问，补充细节。", 但確認字串後會變成"为了更加高效率解决您遇到的问题"顯示在頁面上 -
增加幾個Hotwords時, 問題1的狀況會變更多, 而且有些不是我要增加的名詞也會被取代掉
比如: 設定"Tool,客製化,季會", 有時在語音靜音的狀況下會出現其中一個字, 又或者在不是這個諧音字上也被取代成設定的hotwords
請問以上兩個問題該怎麼處理?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with realtime_ws.py and reproduce both reported cases: compare the continuous partial transcript with the final string sent to the frontend, then test the configured hotwords against silence and similar-sounding text. Done means the final transcript retains the complete spoken content and hotwords replace only the intended terms.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- audio-video-rtc, backend
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100