Store › model › Speech
Fun-ASR-Nano-2512-GGUF
by FunAudioLLM · source Hugging Face · updated 2026-07-29
other997 MB~2 GB RAMsource aliveunlabeled
Standalone audio.cpp GGUF builds of FunAudioLLM/Fun-ASR-Nano-2512-hf. Each file embeds the model configuration, processor configuration, tokenizer, chat template, and the audio.cpp model package spec…
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:FunAudioLLM/Fun-ASR-Nano-2512-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512-GGUF
- License: other (custom license: read it at the source before installing) · text
- Requirements: about 2 GB of RAM, 997 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with whisper.cpp.
- Tags:
audio.cppggufspeech-recognitionmultilingualfunasrautomatic-speech-recognition
Numbers
- 63,470 downloads on Hugging Face
- 8 likes
- license other
- 1.0 GB for fun-asr-nano-2512-q8_0.gguf
- 15,195 npm downloads a week for nodejs-whisper
- latest nodejs-whisper@0.3.1
Numbers as of 2026-10-02 20:59 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
fun-asr-nano-2512-f16.gguf | F16 | 1.6 GB |
fun-asr-nano-2512-q8_0.gguf | Q8_0 | 997 MB |
From the source README
Fun-ASR-Nano-2512 GGUF
Standalone audio.cpp GGUF builds of
FunAudioLLM/Fun-ASR-Nano-2512-hf.
Each file embeds the model configuration, processor configuration, tokenizer,
chat template, and the audio.cpp model package specification.
Files
| File | Size | SHA256 |
| --- | ---: | --- |
| `fun-asr-nano-2512-q8_0.gguf` | 1,045,334,432 bytes | `4d727357574b079b7f43336b2930f39da086ca02f5d8d50872090b4c1c3d5e0a` |
| `fun-asr-nano-2512-f16.gguf` | 1,675,708,832 bytes | `3d906c3ccfed07efef88ff53d6cc94b788b9d2edf1492a5679d041b43e98c5be` |
The source checkpoint is pinned to revision
`854d88f94205cd17d2afdb24332130d86fbe654a`. The source
`model.safetensors` SHA256 is
`335ca3e74917f1156690400e2c344350112950165789cf78ce3d0a367affd821`.
audio.cpp
audiocpp_cli \
--task asr \
--family fun_asr_nano \
--model fun-asr-nano-2512-q8_0.gguf \
--backend cuda \
--audio speech.wav
Fun-ASR-Nano currently provides offline multilingual ASR. It does not expose
streaming or timestamp output. On CUDA, audio.cpp keeps the Q8_0 encoder and
adaptor weights native and loads decoder weights as BF16 by default for stable
logits. An explicit `fun_asr_nano.decoder_weight_type` session option overrides
that default.
Reproducibility
The files were generated with audio.cpp's `audiocpp_gguf` converter:
audiocpp_gguf \
--input model.safetensors \
--root /path/to/Fun-ASR-Nano-2512-hf \
--output fun-asr-nano-2512-q8_0.gguf \
--type q8_0 \
--family fun_asr_nano \
--model-spec model_specs/fun_asr_nano.json
Both formats were checked with `audiocpp_gguf --inspect` and full reference
audio transcription on CPU and NVIDIA H100 CUDA.
Card id model:hf:FunAudioLLM/Fun-ASR-Nano-2512-GGUF · collected 2026-10-02 20:59 UTC · JSON