Skip to content

Release 0.2.0#25

Merged
Popochounet merged 170 commits into
mainfrom
dev
Jul 7, 2026
Merged

Release 0.2.0#25
Popochounet merged 170 commits into
mainfrom
dev

Conversation

@Popochounet

@Popochounet Popochounet commented May 25, 2026

Copy link
Copy Markdown
Contributor
  • MAJOR: Complete refacto with Ray and k8s

  • Client refacto: websocket connection. Client can send anything with interface

  • Complete config files for HuRI, k8s, Clients, Modules

  • New modules:

  1. MIC: vad mic that detect speech
  2. STT: speech to text that transcribe speech with sliding windows
  3. TAG: transcript aggregator to aggregate transcript into one sentence when end of speech
  4. EMO: prosody analysis
  5. EAG: prosody analysis result aggregator
  6. QAG: Question aggregator (Emotion + Transcript)
  7. RAG: Call RAGHandle (Ollama, Qdrant, embedding, history) to get answer as stream
  8. TTS: answer to audio speech
  9. Gesture: gesture generation

bernTP and others added 26 commits July 5, 2026 16:08
…ech' into 31-huri-deployment-cloud-terraform
Signed-off-by: bernTP <49957347+bernTP@users.noreply.github.com>
…ion_in_speech

Aau/#38/recognize emotion in speech
Signed-off-by: bernTP <49957347+bernTP@users.noreply.github.com>
@Popochounet Popochounet marked this pull request as ready for review July 7, 2026 19:30
@Popochounet Popochounet requested a review from bernTP July 7, 2026 19:31

@bernTP bernTP left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM dev

@Popochounet Popochounet merged commit 975ae0d into main Jul 7, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants