HojoAI / Hojo-ASR
Hojo-ASR is a high-performance speech recognition model powered by the LLM decoder.
Why this job: says: speech recognition
What it does
Hojo-ASR-V1 is a high-performance conversational speech recognition model powered by the Qwen3 LLM decoder. It adopts the classic Encoder-Adapter-LLM framework, fully leveraging acoustic fine-grained features and strong LLM semantic capabilities.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 5 months ago
- Stars
- 470
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 0% closed
- 1 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Python 100%
Topics
- asr-model
- llm
Project record
- JobSpeech and audio
- StatusListed
- Commits3
- Forks1
- Watching1
- Stars in 28 days+149
- CreatedMay 25, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026