Comparison
FunASR vs dia2
Verdict
Pick FunASR when license: FunASR is MIT, dia2 is Apache-2.0; pick dia2 when license: dia2 is Apache-2.0, FunASR is MIT.
Markdown twin · FunASR alternatives · dia2 alternatives
GraphCanon updated 1w
Trust & integrity
| Signal | FunASR | dia2 |
|---|---|---|
| Maintenance | Very active (0d since push) As of 3w · github_public_v1 | Slowing (243d since push) As of 3w · github_public_v1 |
| Provenance | Not a fork · Organization account As of 3w · github_public_v1 | Not a fork · Organization account As of 3w · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of 1w · osv@v1 | No lockfile (source not queried) As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- FunASR
- Industrial-grade speech recognition toolkit
- dia2
- TTS model capable of streaming conversational audio in real-time.
Stars
- FunASR
- 20k
- dia2
- 1.2k
Forks
- FunASR
- 2.0k
- dia2
- 99
Open issues
- FunASR
- 5
- dia2
- 5
Language
- FunASR
- Python
- dia2
- Python
Adopt for
- FunASR
- FunASR is an industrial-grade toolkit supporting real-time speech recognition across over 50 languages.
- dia2
- -
Persona
- FunASR
- -
- dia2
- -
Runtime
- FunASR
- -
- dia2
- -
License
- FunASR
- MIT License allows free use and modification.
- dia2
- Apache-2.0
Last pushed
- FunASR
- Jul 30, 2026
- dia2
- Nov 29, 2025
Categories
- FunASR
- Speech & Audio
- dia2
- Speech & Audio
Trust and health
Maintenance
- FunASR
- Very active (96%)
- dia2
- Slowing (36%)
Days since push
- FunASR
- 0d
- dia2
- 243d
Full report
- FunASR
- Trust report
- dia2
- Trust report
Choose FunASR if…
- License: FunASR is MIT, dia2 is Apache-2.0.
- Requirements: Requires Python ≥ 3.8.; PyTorch and torchaudio must be installed separately before running FunASR..
- Tags unique to FunASR: asr, audio, chinese, emotion-recognition.
- When requiring high-speed real-time processing of up to 170x realtime speech recognition.
When NOT to use FunASR
- In scenarios where only a narrow set of languages are required, as overhead for supporting over 50 languages may be unnecessary.
- For projects lacking GPU resources since certain models, like the Fun-ASR-Nano flagship model, require a GPU to run effectively.
Choose dia2 if…
- License: dia2 is Apache-2.0, FunASR is MIT.
- Tags unique to dia2: open-weight, text-to-speech.
- When you need real-time streaming capabilities for text-to-speech applications.
When NOT to use dia2
- For projects aimed at batch processing or non-realtime TTS applications where instantaneous audio output isn't required.
- If you are looking for an open-source model that does not include specific proprietary components like the Kyutai Mimi codec.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (modelscope/FunASR) · observed Jul 30, 2026
- GitHub forks (modelscope/FunASR) · observed Jul 30, 2026
- Last push (modelscope/FunASR) · observed Jul 30, 2026
- License file (MIT) · observed Jul 30, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Aug 16, 2026
- GitHub stars (nari-labs/dia2) · observed Jul 30, 2026
- GitHub forks (nari-labs/dia2) · observed Jul 30, 2026
- Last push (nari-labs/dia2) · observed Nov 29, 2025
- License file (Apache-2.0) · observed Jul 30, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: FunASR 20k · dia2 1.2k (synced Jul 30, 2026).
Common questions
- What is the difference between FunASR and dia2?
- FunASR: Industrial-grade speech recognition toolkit. dia2: TTS model capable of streaming conversational audio in real-time.. See the comparison table for live GitHub stats and shared categories.
- When should I choose FunASR over dia2?
- Choose FunASR over dia2 when License: FunASR is MIT, dia2 is Apache-2.0; Requirements: Requires Python ≥ 3.8.; PyTorch and torchaudio must be installed separately before running FunASR.; Tags unique to FunASR: asr, audio, chinese, emotion-recognition; When requiring high-speed real-time processing of up to 170x realtime speech recognition.
- When should I choose dia2 over FunASR?
- Choose dia2 over FunASR when License: dia2 is Apache-2.0, FunASR is MIT; Tags unique to dia2: open-weight, text-to-speech; When you need real-time streaming capabilities for text-to-speech applications.
- When should I avoid FunASR?
- In scenarios where only a narrow set of languages are required, as overhead for supporting over 50 languages may be unnecessary. For projects lacking GPU resources since certain models, like the Fun-ASR-Nano flagship model, require a GPU to run effectively.
- When should I avoid dia2?
- For projects aimed at batch processing or non-realtime TTS applications where instantaneous audio output isn't required. If you are looking for an open-source model that does not include specific proprietary components like the Kyutai Mimi codec.
- Is FunASR or dia2 more popular on GitHub?
- FunASR has more GitHub stars (19,554 vs 1,160). Stars measure visibility, not whether either tool fits your constraints.
- Are FunASR and dia2 open source?
- Yes - both are open-source projects on GitHub (FunASR: MIT, dia2: Apache-2.0).
- Where can I find alternatives to FunASR or dia2?
- GraphCanon lists graph-backed alternatives at FunASR alternatives and dia2 alternatives (FunASR markdown twin, dia2 markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, FunASR or dia2?
- FunASR: Very active. dia2: Slowing. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for FunASR and dia2?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: FunASR trust report; dia2 trust report.