Hacktoberfest 2026:维护者为十月标记出来的 issue,仍然开放、适合新手。 浏览 Hacktoberfest issue

Spoken translation through the glasses speaker

未关闭
#187 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
4/5
预计耗时
3-5 天
新手友好度
22/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
c, python

调研方向

Start with the voice pipeline in sentient/voice/stt.py, sentient/voice/tts.py and sentient/voice/session.py, then the audio output in firmware/esp32s3-glasses/main/audio.c and the phone captions under sentient/nodes/web/. The issue does not pick a translation model, so that choice needs a maintainer decision first. Done means speech in one language is spoken back in another through the glasses within a few seconds, and captions appear on the phone.

由索引模型根据 Issue 内容生成。

描述

area: devices area: voice enhancement help wanted priority: P2 size: M

Even G2 has no speaker, so it cannot voice translations, and its accuracy drops in noise. On Meta's Display glasses translation is praised but reviews vary. Quality from 8B general models is the main risk.

Idea: Live translation using a dedicated local MT or Whisper-translate model, spoken through the glasses' MAX98357A speaker, with captions on the phone.

Status in Sentient today: New.

Where: sentient/voice/stt.py and sentient/voice/tts.py, a translation mode in sentient/voice/session.py, audio out in firmware/esp32s3-glasses/main/audio.c, captions in the phone web app under sentient/nodes/web/.

Done when:

  • speech in one language is spoken back in another through the glasses within a few seconds
  • captions appear on the phone

Sources:

Roadmap ID: VOICE-5 · Priority: P2 · Size: M

主要语言
Python
星标
702
派生
113
平均合并
5 小时 8 分钟
30 天内合并 PR
171

环境准备

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

existence-master/Sentient 的其他 Issue

查看 existence-master/Sentient 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。