--- title: "Fun-ASR vs TensorFlowASR" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/funaudiollm-fun-asr-vs-tensorspeech-tensorflowasr" tools: ["funaudiollm-fun-asr", "tensorspeech-tensorflowasr"] --- # Fun-ASR vs TensorFlowASR *GraphCanon updated Jul 31, 2026* ## Verdict Pick Fun-ASR if fun-ASR is a real-time speech recognition tool supporting 31 languages with capabilities for handling dialects, accents, and speaker diarization; pick TensorFlowASR if tensorFlowASR is an advanced Automatic Speech Recognition library built on TensorFlow 2 that supports modern architectures such as Conformer and RNN-Transducer. [Fun-ASR](https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano) reports 1.4k GitHub stars, 141 forks, and 0 open issues, last pushed Jul 24, 2026. [TensorFlowASR](https://huylenguyen.com/asr) has 1.0k stars, 239 forks, and 47 open issues, last pushed Jul 30, 2026. Figures are from public GitHub metadata via [Fun-ASR's repository](https://github.com/FunAudioLLM/Fun-ASR) and [TensorFlowASR's repository](https://github.com/TensorSpeech/TensorFlowASR). | | [Fun-ASR](/tools/funaudiollm-fun-asr.md) | [TensorFlowASR](/tools/tensorspeech-tensorflowasr.md) | | --- | --- | --- | | Tagline | Fun-ASR-Nano LLM-ASR model supports 31 languages for real-time speech recognition tasks | Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2 | | Stars | 1,449 | 1,010 | | Forks | 141 | 239 | | Open issues | 0 | 47 | | Language | C | Python | | Adopt for | Fun-ASR is a real-time speech recognition tool supporting 31 languages with capabilities for handling dialects, accents, and speaker diarization. | TensorFlowASR is an advanced Automatic Speech Recognition library built on TensorFlow 2 that supports modern architectures such as Conformer and RNN-Transducer. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Apache-2.0 | | Categories | LLM Frameworks, Speech & Audio | Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [Fun-ASR](/tools/funaudiollm-fun-asr.md) | [TensorFlowASR](/tools/tensorspeech-tensorflowasr.md) | | --- | --- | --- | | Days since push | 6d | 0d | | Open issues (now) | 0 | 47 | | Full report | [trust report](/tools/funaudiollm-fun-asr/trust.md) | [trust report](/tools/tensorspeech-tensorflowasr/trust.md) | ## Shared compatibility - **Python**: [Fun-ASR](/tools/funaudiollm-fun-asr.md) - Python runtime; [TensorFlowASR](/tools/tensorspeech-tensorflowasr.md) - Python runtime ## Decision facts: Fun-ASR - **Pricing:** freemium - Open source under Apache License 2.0 allows free use with attribution and adherence to the license terms. - **Requirements:** Installation requires Python packages `funasr` version >=1.3.3, and `vllm` version >=0.12.0. - **Adopt for:** Fun-ASR is a real-time speech recognition tool supporting 31 languages with capabilities for handling dialects, accents, and speaker diarization. - **License detail:** Apache-2.0 ## Decision facts: TensorFlowASR - **Adopt for:** TensorFlowASR is an advanced Automatic Speech Recognition library built on TensorFlow 2 that supports modern architectures such as Conformer and RNN-Transducer. - **License detail:** Apache-2.0 ## Choose when ### Choose Fun-ASR if… - Fun-ASR is primarily C; TensorFlowASR is Python. - Pricing: Open source under Apache License 2.0 allows free use with attribution and adherence to the license terms.. - Requirements: Installation requires Python packages `funasr` version >=1.3.3, and `vllm` version >=0.12.0.. - Tags unique to Fun-ASR: asr, audio-language-model, multilingual-asr, real-time-asr. - Also covers LLM Frameworks. - When you need support for 31 different languages including handling of various dialects and accents. ### Choose TensorFlowASR if… - TensorFlowASR is primarily Python; Fun-ASR is C. - Tags unique to TensorFlowASR: automatic-speech-recognition, conformer, contextnet, ctc. - TensorFlowASR ships Docker support for self-hosted deployment. - When focusing on state-of-the-art performance with models like Conformer or ContextNet, which are among its supported architectures and not necessarily included in all ASR libraries. ## When NOT to use Fun-ASR - Avoid if your project requires a specific programming language other than C as Fun-ASR is primarily developed in C. - If you do not require on-device processing, as this tool is designed for on-device inference which may limit scalability for cloud-based applications. ## When NOT to use TensorFlowASR - When Python version constraints are an issue, as TensorFlowASR strictly requires python >= 3.12 on Apple Silicon devices, limiting compatibility. - If your project cannot accommodate the extra installation steps involving `ctc_decoders` and `rnnt_loss`, which implies additional complexity in setting up the environment. ## Common questions ### What is the difference between Fun-ASR and TensorFlowASR? Fun-ASR: Fun-ASR-Nano LLM-ASR model supports 31 languages for real-time speech recognition tasks. TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. See the comparison table for live GitHub stats and shared categories. ### When should I choose Fun-ASR over TensorFlowASR? Choose Fun-ASR over TensorFlowASR when Fun-ASR is primarily C; TensorFlowASR is Python; Pricing: Open source under Apache License 2.0 allows free use with attribution and adherence to the license terms.; Requirements: Installation requires Python packages `funasr` version >=1.3.3, and `vllm` version >=0.12.0.; Tags unique to Fun-ASR: asr, audio-language-model, multilingual-asr, real-time-asr; Also covers LLM Frameworks; When you need support for 31 different languages including handling of various dialects and accents. ### When should I choose TensorFlowASR over Fun-ASR? Choose TensorFlowASR over Fun-ASR when TensorFlowASR is primarily Python; Fun-ASR is C; Tags unique to TensorFlowASR: automatic-speech-recognition, conformer, contextnet, ctc; TensorFlowASR ships Docker support for self-hosted deployment; When focusing on state-of-the-art performance with models like Conformer or ContextNet, which are among its supported architectures and not necessarily included in all ASR libraries. ### When should I avoid Fun-ASR? Avoid if your project requires a specific programming language other than C as Fun-ASR is primarily developed in C. If you do not require on-device processing, as this tool is designed for on-device inference which may limit scalability for cloud-based applications. ### When should I avoid TensorFlowASR? When Python version constraints are an issue, as TensorFlowASR strictly requires python >= 3.12 on Apple Silicon devices, limiting compatibility. If your project cannot accommodate the extra installation steps involving `ctc_decoders` and `rnnt_loss`, which implies additional complexity in setting up the environment. ### Is Fun-ASR or TensorFlowASR more popular on GitHub? Fun-ASR has more GitHub stars (1,449 vs 1,010). Stars measure visibility, not whether either tool fits your constraints. ### Are Fun-ASR and TensorFlowASR open source? Yes - both are open-source projects on GitHub (Fun-ASR: Apache-2.0, TensorFlowASR: Apache-2.0). ### Where can I find alternatives to Fun-ASR or TensorFlowASR? GraphCanon lists graph-backed alternatives at [Fun-ASR alternatives](/tools/funaudiollm-fun-asr/alternatives) and [TensorFlowASR alternatives](/tools/tensorspeech-tensorflowasr/alternatives) ([Fun-ASR markdown twin](/tools/funaudiollm-fun-asr/alternatives.md), [TensorFlowASR markdown twin](/tools/tensorspeech-tensorflowasr/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/funaudiollm-fun-asr-vs-tensorspeech-tensorflowasr.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, Fun-ASR or TensorFlowASR? Fun-ASR: Very active. TensorFlowASR: Very active. 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 Fun-ASR and TensorFlowASR? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Fun-ASR trust report](/tools/funaudiollm-fun-asr/trust); [TensorFlowASR trust report](/tools/tensorspeech-tensorflowasr/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=funaudiollm-fun-asr`](/api/graphcanon/graph?tool=funaudiollm-fun-asr) - 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/_