Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

docs(README): benchmark shows flagship Fun-ASR-Nano vLLM speed (340x), not the torch number (#3023)

zhifu gao11fe7db83df8
diff --git a/README.md b/README.md
index 6008e4e68..cd5620fe8 100644
--- a/README.md
+++ b/README.md
@@ -113,10 +113,10 @@ Trying FunASR for the first time? Use the [Colab quickstart](./examples/colab/)
| Model | GPU Speed | CPU Speed | vs Whisper-large-v3 |
|-------|-----------|-----------|-------------------|
+| **Fun-ASR-Nano** (vLLM) | **340x** realtime | — | 🚀 **26x faster** |
| **SenseVoice-Small** | **170x** realtime | **17x** realtime | 🚀 **13x faster** |
| **Paraformer-Large** | **120x** realtime | **15x** realtime | 🚀 **9x faster** |
| Whisper-large-v3-turbo | 46x realtime | ❌ | 3.4x faster |
-| **Fun-ASR-Nano** | 17x realtime | 3.6x realtime | 1.3x faster |
| Whisper-large-v3 | 13x realtime | ❌ | baseline |
> **Key takeaway:** FunASR models run on CPU faster than Whisper runs on GPU.