--- title: "BELLE vs Amphion" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/lianjiatech-belle-vs-open-mmlab-amphion" tools: ["lianjiatech-belle", "open-mmlab-amphion"] --- # BELLE vs Amphion *GraphCanon updated Sep 20, 2026* ## Verdict Pick BELLE if bELLE is an open-source Chinese dialogue large model project that focuses on making high-quality instruction-following language models accessible to everyone. It provides instruction training data, models, training code,; pick Amphion if amphion offers support for reproducible research in audio, music, and speech generation through Python dependencies and Docker images that junior researchers and engineers can readily use. [BELLE](https://github.com/LianjiaTech/BELLE) reports 8.3k GitHub stars, 755 forks, and 106 open issues, last pushed Oct 16, 2024. [Amphion](https://openhlt.github.io/amphion/) has 10k stars, 851 forks, and 175 open issues, last pushed Mar 25, 2026. Figures are from public GitHub metadata via [BELLE's repository](https://github.com/LianjiaTech/BELLE) and [Amphion's repository](https://github.com/open-mmlab/Amphion). | | [BELLE](/tools/lianjiatech-belle.md) | [Amphion](/tools/open-mmlab-amphion.md) | | --- | --- | --- | | Tagline | Open-source Chinese dialogue large model | A toolkit for Audio, Music, and Speech Generation to support reproducible research | | Stars | 8,270 | 10,303 | | Forks | 755 | 851 | | Open issues | 106 | 175 | | Language | HTML | Python | | Adopt for | BELLE is an open-source Chinese dialogue large model project that focuses on making high-quality instruction-following language models accessible to everyone. It provides instruction training data, models, training code, | Amphion offers support for reproducible research in audio, music, and speech generation through Python dependencies and Docker images that junior researchers and engineers can readily use. | | Persona | - | - | | Runtime | - | - | | License | BELLE is licensed under Apache-2.0, allowing for free use, modification, and distribution. | MIT | | Categories | Computer Vision, Evaluation & Observability, LLM Frameworks, Model Training, Speech & Audio | Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [BELLE](/tools/lianjiatech-belle.md) | [Amphion](/tools/open-mmlab-amphion.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Slowing (36%) | | Days since push | 701d | 178d | | Open issues (now) | 106 | 175 | | Stars delta | -10 (30d) | +330 (30d) | | Full report | [trust report](/tools/lianjiatech-belle/trust.md) | [trust report](/tools/open-mmlab-amphion/trust.md) | ## Decision facts: BELLE - **Requirements:** Min 8 GB RAM; Requires Docker; BELLE requires Docker for running the environment.; Ensure you have sufficient computational resources for training and inference. - **Adopt for:** BELLE is an open-source Chinese dialogue large model project that focuses on making high-quality instruction-following language models accessible to everyone. It provides instruction training data, models, training code, - **License detail:** BELLE is licensed under Apache-2.0, allowing for free use, modification, and distribution. ## Decision facts: Amphion - **Adopt for:** Amphion offers support for reproducible research in audio, music, and speech generation through Python dependencies and Docker images that junior researchers and engineers can readily use. ## Choose when ### Choose BELLE if… - BELLE is primarily HTML; Amphion is Python. - License: BELLE is Apache-2.0, Amphion is MIT. - Requirements: Min 8 GB RAM; Requires Docker; BELLE requires Docker for running the environment.; Ensure you have sufficient computational resources for training and inference.. - Tags unique to BELLE: bloom, chinese-nlp, gpt-evaluation, gpt-q. - Also covers Computer Vision, Evaluation & Observability, LLM Frameworks, Model Training. - Use BELLE when you need a Chinese-specific large language model that has been optimized for instruction-following tasks. ### Choose Amphion if… - Amphion is primarily Python; BELLE is HTML. - License: Amphion is MIT, BELLE is Apache-2.0. - Tags unique to Amphion: audio-generation, music-generation, singing-voice-conversion, speech-synthesis. - Amphion ships Docker support for self-hosted deployment. - When you are new to the field of audio, music, or speech generation and seeking a toolkit that simplifies setup with Python dependencies and Docker images. ## When NOT to use BELLE - Avoid BELLE if your project requires a language model that is not focused on Chinese, as it is specifically optimized for the Chinese language. - Do not use BELLE if you need a model that is trained on a diverse set of data beyond Chinese dialogue, as it primarily uses data generated by ChatGPT. - BELLE may not be suitable if you require a model that has not been fine-tuned on high-quality dialogue data, as it emphasizes instruction-following capabilities. ## When NOT to use Amphion - If you require advanced customization beyond what the provided Python packages offer, since Amphion caters more to getting started quickly without deep configuration. ## Common questions ### What is the difference between BELLE and Amphion? BELLE: Open-source Chinese dialogue large model. Amphion: A toolkit for Audio, Music, and Speech Generation to support reproducible research. See the comparison table for live GitHub stats and shared categories. ### When should I choose BELLE over Amphion? Choose BELLE over Amphion when BELLE is primarily HTML; Amphion is Python; License: BELLE is Apache-2.0, Amphion is MIT; Requirements: Min 8 GB RAM; Requires Docker; BELLE requires Docker for running the environment.; Ensure you have sufficient computational resources for training and inference.; Tags unique to BELLE: bloom, chinese-nlp, gpt-evaluation, gpt-q; Also covers Computer Vision, Evaluation & Observability, LLM Frameworks, Model Training; Use BELLE when you need a Chinese-specific large language model that has been optimized for instruction-following tasks. ### When should I choose Amphion over BELLE? Choose Amphion over BELLE when Amphion is primarily Python; BELLE is HTML; License: Amphion is MIT, BELLE is Apache-2.0; Tags unique to Amphion: audio-generation, music-generation, singing-voice-conversion, speech-synthesis; Amphion ships Docker support for self-hosted deployment; When you are new to the field of audio, music, or speech generation and seeking a toolkit that simplifies setup with Python dependencies and Docker images. ### When should I avoid BELLE? Avoid BELLE if your project requires a language model that is not focused on Chinese, as it is specifically optimized for the Chinese language. Do not use BELLE if you need a model that is trained on a diverse set of data beyond Chinese dialogue, as it primarily uses data generated by ChatGPT. BELLE may not be suitable if you require a model that has not been fine-tuned on high-quality dialogue data, as it emphasizes instruction-following capabilities. ### When should I avoid Amphion? If you require advanced customization beyond what the provided Python packages offer, since Amphion caters more to getting started quickly without deep configuration. ### Is BELLE or Amphion more popular on GitHub? Amphion has more GitHub stars (10,303 vs 8,270). Stars measure visibility, not whether either tool fits your constraints. ### Are BELLE and Amphion open source? Yes - both are open-source projects on GitHub (BELLE: Apache-2.0, Amphion: MIT). ### Where can I find alternatives to BELLE or Amphion? GraphCanon lists graph-backed alternatives at [BELLE alternatives](/tools/lianjiatech-belle/alternatives) and [Amphion alternatives](/tools/open-mmlab-amphion/alternatives) ([BELLE markdown twin](/tools/lianjiatech-belle/alternatives.md), [Amphion markdown twin](/tools/open-mmlab-amphion/alternatives.md)), 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](/compare/lianjiatech-belle-vs-open-mmlab-amphion.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, BELLE or Amphion? BELLE: Dormant. Amphion: 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 BELLE and Amphion? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [BELLE trust report](/tools/lianjiatech-belle/trust); [Amphion trust report](/tools/open-mmlab-amphion/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=lianjiatech-belle`](/api/graphcanon/graph?tool=lianjiatech-belle) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_