Update model card

README.md

@@ -0,0 +1,115 @@
+---
+language:
+- en
+library_name: stable-audio-3
+license: other
+license_name: stable-audio-community
+license_link: LICENSE
+pipeline_tag: text-to-audio
+---
+
+# Stable Audio 3 Medium (Base)
+
+> **Note:** This is the base (pre-trained) model intended for fine-tuning. If you are looking to generate audio directly, please use [Stable Audio 3 Medium](https://huggingface.co/stabilityai/stable-audio-3-medium) instead.
+
+![Stable Audio 3 logo](./Stable_Audio_3.0_Thumbnail_1x1.png)
+
+Please note: For commercial use, please refer to [https://stability.ai/license](https://stability.ai/license)
+
+## Model Description
+`Stable Audio 3` is a family of fast latent diffusion models (small, medium, large) for variable length audio generation and editing. Since our models can generate several minutes of audio,
+variable-length generations are key to avoid the cost of producing full-length generations for short
+sounds. We also support inpainting, enabling targeted audio editing and the continuation of short
+recordings. Our latent diffusion models operate on top of a novel semantic-acoustic autoencoder that
+projects audio into a compact latent space, enabling efficient diffusion-based generation while preserving audio fidelity and encouraging semantic structure in the latent. Finally, we run adversarial
+post-training to both accelerate inference and improve generation quality, reducing the number of inference steps while improving fidelity and prompt adherence. Stable Audio 3 models are trained on
+licensed and Creative Commons data to generate music and sounds in less than a 2s on an H200 GPU
+and less than a few seconds on a MacBook Pro M4. We release the weights of small and medium,
+that can run on consumer-grade hardware, together with their training and inference pipeline.
+
+## Usage
+
+This model can be used with:
+1. the [`stable-audio-3`](https://github.com/Stability-AI/stable-audio-3) inference and fine-tuning library
+2. the [`stable-audio-tools`](https://github.com/Stability-AI/stable-audio-tools) research library
+
+
+### Using with `stable-audio-3`
+from stable_audio_3 import StableAudioModel
+
+model = StableAudioModel.from_pretrained("medium-base")
+audio = model.generate(
+    prompt="House music that encapsulates the feeling of being at a festival in the sunny weather with all your friends 124 BPM",
+    duration=180,
+)
+
+
+### Using with `stable-audio-tools`
+
+```python
+import torch
+import torchaudio
+from einops import rearrange
+from stable_audio_tools import get_pretrained_model
+from stable_audio_tools.inference.generation import generate_diffusion_cond_inpaint
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+if device == "cuda":
+  model_half = True
+
+# Download model
+model, model_config = get_pretrained_model("stabilityai/stable-audio-3-medium-base")
+sample_rate = model_config["sample_rate"]
+sample_size = model_config["sample_size"]
+
+model = model.to(device)
+if model_half:
+  model = model.to(torch.float16)
+# Set up text and timing conditioning
+conditioning = [{
+    "prompt": "A dream-like Synthpop instrumental that would accompany a dream-sequence in a surrealist movie 120 BPM",
+    "seconds_total": 380
+}]
+
+# Generate stereo audio
+output = generate_diffusion_cond_inpaint(
+    model,
+    steps=8,
+    cfg_scale=1.0,
+    conditioning=conditioning,
+    sample_size=sample_size,
+    sampler_type="pingpong",
+    device=device
+)
+
+# Rearrange audio batch to a single sequence
+output = rearrange(output, "b d n -> d (b n)")
+
+# Peak normalize, clip, convert to int16, and save to file
+output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu()
+torchaudio.save("output.wav", output, sample_rate)
+```
+
+
+## Model Details
+* **Model type**: `Stable Audio Open 3` is a latent diffusion model based on a transformer architecture.
+* **Language(s)**: English
+* **License**: [Stability AI Community License](https://huggingface.co/stabilityai/stable-audio-3/blob/main/LICENSE.md).
+* **Commercial License**: to use this model commercially, please refer to [https://stability.ai/license](https://stability.ai/license)
+* **Research Paper**: [https://arxiv.org/abs/2605.17991](https://arxiv.org/abs/2605.17991)
+
+We use a publicly available pre-trained T5Gemma model ([t5gemma-b-b-ul2](https://huggingface.co/google/t5gemma-b-b-ul2)) for text conditioning. T5Gemma is redistributed under the [Gemma Terms of Use](LICENSE_GEMMA.md).
+
+## Training dataset
+
+### Datasets Used
+Our dataset consists of 1,278,902 audio recordings, where 806,284 recordings are licensed from [Audiosparx](https://www.audiosparx.com/) and a further 472,618 are from [Freesound](https://freesound.org/). 
+The Freesound portion consists of recordings licensed under CC-0, CC-BY, or CCSampling+. To ensure no copyrighted content was present in the Freesound data, music recordings were identified
+using the PANNs [89] tagger. We flagged audio that activated music-related tags for at least 30s (threshold of 0.15),
+that was sent to a trusted content detection company to verify the absence of copyrighted material. All identified copyrighted content was removed. After filtering, the Freesound part includes 266,324 CC-0, 194,840 CC-BY, and 11,454
+CC-Sampling+ recordings. The same subset of Freesound audio we used to train Stable Audio Open: https://info.stability.ai/attributions. All stable-audio-3 small models are initially pre-trained on a mixture of AudioSparx and Freesound.
+But for the final stage of pre-training, distillation warmup, and post-training, we use AudioSparx for small-music
+and a higher-quality subset of Freesound for small-sfx. As a result, note that medium and large models are able to
+handle both music and sound effect generation within a single unified model. However, we find that for small models
+the inclusion of sound effects data degrades musical coherence. By isolating the sound effects subset into small-sfx,
+we mitigate this interference and obtain improved perceptual quality in both domains.