Comparison
FunASR vs LLMs-from-scratch
Verdict
Pick FunASR when funASR is primarily Python; LLMs-from-scratch is Jupyter Notebook; pick LLMs-from-scratch when lLMs-from-scratch is primarily Jupyter Notebook; FunASR is Python.
Markdown twin · FunASR alternatives · LLMs-from-scratch alternatives
GraphCanon updated today
vs
Trust & integrity
| Signal | FunASR | LLMs-from-scratch |
|---|---|---|
| Maintenance | Very active (1d since push) As of today · github_public_v1 | Steady (38d since push) As of today · github_public_v1 |
| Provenance | Not a fork · Organization account As of today · github_public_v1 | Not a fork · Personal account As of today · github_public_v1 |
| Security (OSV) | No criticals As of today · mcp_manifest@v1 | No lockfile As of today · none |
Tagline
- FunASR
- Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
- LLMs-from-scratch
- Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Stars
- FunASR
- 19k
- LLMs-from-scratch
- 99k
Forks
- FunASR
- 1.9k
- LLMs-from-scratch
- 15k
Open issues
- FunASR
- 1
- LLMs-from-scratch
- 4
Language
- FunASR
- Python
- LLMs-from-scratch
- Jupyter Notebook
Adopt for
- FunASR
- -
- LLMs-from-scratch
- LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions.
Persona
- FunASR
- -
- LLMs-from-scratch
- -
Runtime
- FunASR
- -
- LLMs-from-scratch
- -
License
- FunASR
- MIT
- LLMs-from-scratch
- Other
Last pushed
- FunASR
- Jul 10, 2026
- LLMs-from-scratch
- Jun 2, 2026
Categories
- FunASR
- LLM Frameworks, Model Training, Inference & Serving
- LLMs-from-scratch
- Model Training, LLM Frameworks
Trust and health
Maintenance
- FunASR
- Very active (96%)
- LLMs-from-scratch
- Steady (60%)
Days since push
- FunASR
- 1d
- LLMs-from-scratch
- 38d
Open issues (now)
- FunASR
- 1
- LLMs-from-scratch
- 4
Owner type
- FunASR
- Organization
- LLMs-from-scratch
- User
Security scan
- FunASR
- No criticals
- LLMs-from-scratch
- No lockfile
Full report
- FunASR
- Trust report
- LLMs-from-scratch
- Trust report
Choose FunASR if…
- FunASR is primarily Python; LLMs-from-scratch is Jupyter Notebook.
- License: FunASR is MIT, LLMs-from-scratch is Other.
- Tags unique to FunASR: mcp-server, asr, chinese, multilingual-asr.
- Also covers Inference & Serving.
When NOT to use FunASR
- LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.
- Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge.
- Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic.
Choose LLMs-from-scratch if…
- LLMs-from-scratch is primarily Jupyter Notebook; FunASR is Python.
- License: LLMs-from-scratch is Other, FunASR is MIT.
- Tags unique to LLMs-from-scratch: deep-learning, ai, artificial-intelligence, attention-mechanism.
- - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.
When NOT to use LLMs-from-scratch
- - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work.
- - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰
- a deeper learning experience.
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 11, 2026
- GitHub forks (modelscope/FunASR) · observed Jul 11, 2026
- Last push (modelscope/FunASR) · observed Jul 10, 2026
- License file (MIT) · observed Jul 11, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (rasbt/LLMs-from-scratch) · observed Jul 11, 2026
- GitHub forks (rasbt/LLMs-from-scratch) · observed Jul 11, 2026
- Last push (rasbt/LLMs-from-scratch) · observed Jun 2, 2026
- License file (Other) · observed Jul 11, 2026
- Decision facts (enrichment) · observed Jul 11, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: FunASR 19k · LLMs-from-scratch 99k (synced Jul 11, 2026).
Common questions
- What is the difference between FunASR and LLMs-from-scratch?
- FunASR: Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.. LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. See the comparison table for live GitHub stats and shared categories.
- When should I choose FunASR over LLMs-from-scratch?
- Choose FunASR over LLMs-from-scratch when FunASR is primarily Python; LLMs-from-scratch is Jupyter Notebook; License: FunASR is MIT, LLMs-from-scratch is Other; Tags unique to FunASR: mcp-server, asr, chinese, multilingual-asr; Also covers Inference & Serving.
- When should I choose LLMs-from-scratch over FunASR?
- Choose LLMs-from-scratch over FunASR when LLMs-from-scratch is primarily Jupyter Notebook; FunASR is Python; License: LLMs-from-scratch is Other, FunASR is MIT; Tags unique to LLMs-from-scratch: deep-learning, ai, artificial-intelligence, attention-mechanism; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.
- When should I avoid FunASR?
- LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic.
- When should I avoid LLMs-from-scratch?
- - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 a deeper learning experience.
- Is FunASR or LLMs-from-scratch more popular on GitHub?
- LLMs-from-scratch has more GitHub stars (98,899 vs 19,141). Stars measure visibility, not whether either tool fits your constraints.
- Are FunASR and LLMs-from-scratch open source?
- Yes - both are open-source projects on GitHub (FunASR: MIT, LLMs-from-scratch: Other).
- Where can I find alternatives to FunASR or LLMs-from-scratch?
- GraphCanon lists graph-backed alternatives at FunASR alternatives and LLMs-from-scratch alternatives (FunASR markdown twin, LLMs-from-scratch 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 LLMs-from-scratch?
- FunASR: Very active. LLMs-from-scratch: Steady. 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 LLMs-from-scratch?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: FunASR trust report; LLMs-from-scratch trust report.