Upload README.md with huggingface_hub

README.md

@@ -95,6 +95,8 @@ Training first optimizes the semantic codebook, then jointly trains all eight co
 
 ## How to Use
 
+MiniMax Music 3 is supported by [SGLang-Omni](https://github.com/sgl-project/sglang-omni). Follow the official [installation guide](https://sgl-project.github.io/sglang-omni/get_started/installation.html) to prepare the runtime environment.
+
 ### Download the Model
 
 ```bash
@@ -103,41 +105,40 @@ hf download MiniMaxAI/MiniMax-Music3 --local-dir /path/to/minimax_ttm
 
 ### Serve with SGLang-Omni
 
-MiniMax Music 3 is currently supported by [SGLang-Omni](https://github.com/sgl-project/sglang-omni). From the SGLang-Omni repository root, run:
-
 ```bash
-python -m sglang_omni.cli serve \
-  --config examples/configs/minimax_ttm.yaml \
+sgl-omni serve \
   --model-path /path/to/minimax_ttm \
-  --host 127.0.0.1 \
   --port 8000
 ```
 
-Inference uses two CUDA GPUs:
-
-- **GPU 0** runs Qwen3 and eight-codebook RVQ autoregressive generation.
-- **GPU 1** runs Flow Matching and DAV waveform decoding.
-
 ### Generate Music
 
-The service uses the shared speech API. Put the lyrics in `input` and the music description in `instructions`.
+The service uses the shared speech API. Put the lyrics in `input` and the music description in `instructions`. Put lyric structure tags such as `[Verse]` and `[Chorus]` on their own lines.
 
 ```bash
 curl http://127.0.0.1:8000/v1/audio/speech \
   -H 'Content-Type: application/json' \
   -d '{
-    "model": "minimax_ttm",
+    "model": "MiniMaxAI/MiniMax-Music3",
     "input": "[Verse]\nMorning light filtering through the pine\n[Chorus]\nSoftly the world begins to breathe",
     "instructions": "A warm acoustic pop song with intimate female vocals, fingerpicked guitar, soft piano, and a gradual emotional build into a wide final chorus.",
     "response_format": "wav",
     "seed": 7,
-    "max_new_tokens": 9000,
+    "max_new_tokens": 750,
     "stream": false
   }' \
   --output minimax_music3.wav
 ```
 
-An example generated with this checkpoint is available at [`assets/minimax_ttm.wav`](assets/minimax_ttm.wav).
+`max_new_tokens` sets the maximum number of audio frames at 25 frames per second. Generation may finish before this limit when the model emits an end-of-audio token. The response is a 32 kHz, 16-bit stereo WAV file.
+
+### Reproducible Example
+
+The following end-to-end example contains the complete lyrics, music description, and generation parameters used to produce the reference audio.
+
+| Use case | Request | Result |
+|---|---|---|
+| Text-to-music | [View script](https://huggingface.co/MiniMaxAI/MiniMax-Music3/blob/main/scripts/end_to_end/minimax_ttm_test.py) | [minimax_ttm.wav](https://huggingface.co/MiniMaxAI/MiniMax-Music3/blob/main/assets/minimax_ttm.wav) |
 
 ## Prompt Enhancement
 
@@ -145,7 +146,7 @@ A concise natural-language description can be used directly. For more detailed c
 
 ## Limitations
 
-- Inference requires two CUDA GPUs.
+- Inference requires CUDA.
 - Only non-streaming generation is currently supported.
 - The tokenized text prompt is limited to 5,000 tokens.
 - Audio generation is limited to 9,000 acoustic frames.