Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,37 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+freesound_dataset_attribution2.csv filter=lfs diff=lfs merge=lfs -text
+Stable_audio_open.jpg filter=lfs diff=lfs merge=lfs -text

LICENSE.md

@@ -0,0 +1,58 @@
+STABILITY AI COMMUNITY LICENSE AGREEMENT
+	
+Last Updated: July 5, 2024
+
+1. INTRODUCTION
+
+This Agreement applies to any individual person or entity (“You”, “Your” or “Licensee”) that uses or distributes any portion or element of the Stability AI Materials  or Derivative Works thereof for any Research & Non-Commercial or Commercial purpose. Capitalized terms not otherwise defined herein are defined in Section V below.
+
+This Agreement is intended to allow research, non-commercial, and limited commercial uses of the Models free of charge. In order to ensure that certain limited commercial uses of the Models continue to be allowed, this Agreement  preserves free access to the Models for people or organizations  generating annual revenue of less than US $1,000,000 (or local currency equivalent).  
+
+By clicking “I Accept”  or by using or distributing or using any portion or element of the Stability Materials or Derivative Works, You agree that You have read, understood and are bound by the terms of this Agreement. If You are acting on behalf of a company, organization or other entity, then “You” includes you and that entity, and You agree that You: (i) are an authorized representative of such entity with the authority to bind such entity to this Agreement, and (ii) You agree to the terms of this Agreement on that entity’s behalf. 
+
+2. RESEARCH & NON-COMMERCIAL USE LICENSE
+
+Subject to the terms of this Agreement, Stability AI grants You a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable and royalty-free limited license under Stability AI’s intellectual property or other rights owned by Stability AI embodied in the Stability AI Materials to use, reproduce, distribute, and create Derivative Works of, and make modifications to, the Stability AI Materials for any Research or Non-Commercial Purpose. “Research Purpose” means academic or scientific advancement, and in each case, is not primarily intended for commercial advantage or monetary compensation to You or others. “Non-Commercial Purpose” means any purpose other than a Research Purpose that is not primarily intended for commercial advantage or monetary compensation to You or others, such as personal use (i.e., hobbyist) or evaluation and testing.  
+
+3. COMMERCIAL USE LICENSE
+
+Subject to the terms of this Agreement (including the remainder of this Section III), Stability AI grants You a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable and royalty-free limited license under Stability AI’s intellectual property or other rights owned by Stability AI embodied in the Stability AI Materials to use, reproduce, distribute, and create Derivative Works of, and make modifications to, the Stability AI Materials for any Commercial Purpose. “Commercial Purpose” means any purpose other than a Research Purpose or Non-Commercial Purpose that is primarily intended for commercial advantage or monetary compensation to You or others, including but not limited to, (i) creating, modifying, or distributing Your product or service, including via a hosted service or application programming interface, and (ii) for Your business’s or organization’s internal operations. 
+If You are using or distributing the Stability AI Materials for a Commercial Purpose, You must register with Stability AI at (https://stability.ai/community-license). If at any time You or Your Affiliate(s), either individually or in aggregate, generate more than USD $1,000,000 in annual revenue (or the equivalent thereof in Your local currency), regardless of whether that revenue is generated directly or indirectly from the Stability AI Materials or Derivative Works, any licenses granted to You under this Agreement shall terminate as of such date. You must request a license from Stability AI at (https://stability.ai/enterprise) , which Stability AI may grant to You in its sole discretion. If you receive Stability AI Materials, or any Derivative Works thereof, from a Licensee as part of an integrated end user product, then Section III of this Agreement will not apply to you.
+
+4. GENERAL TERMS
+
+Your Research, Non-Commercial, and Commercial License(s) under this Agreement are subject to the following terms.
+a.  Distribution & Attribution. If You distribute or make available the Stability AI Materials or a Derivative Work to a third party, or a product or service that uses any portion of them, You shall: (i) provide a copy of this Agreement to that third party, (ii) retain the following attribution notice within a "Notice" text file distributed as a part of such copies: "This Stability AI Model is licensed under the Stability AI Community License, Copyright ©  Stability AI Ltd. All Rights Reserved”, and (iii) prominently display “Powered by Stability AI” on a related website, user interface, blogpost, about page, or product documentation.  If You create a Derivative Work, You may add your own attribution notice(s) to the “Notice” text file included with that Derivative Work, provided that You clearly indicate which attributions apply to the Stability AI Materials and state in the “Notice” text file that You changed the Stability AI Materials and how it was modified.
+b.  Use Restrictions. Your use of the Stability AI Materials and Derivative Works, including any output or results of the Stability AI Materials or Derivative Works, must comply with applicable laws and regulations (including Trade Control Laws and equivalent regulations) and adhere to the Documentation and Stability AI’s AUP, which is hereby incorporated by reference. Furthermore, You will not use the Stability AI Materials or Derivative Works, or any output or results of the Stability AI Materials or Derivative Works, to create or improve any foundational generative AI model (excluding the Models or Derivative Works). 
+c.  Intellectual Property. 
+(i) Trademark License.  No trademark licenses are granted under this Agreement, and in connection with the Stability AI Materials or Derivative Works, You may not use any name or mark owned by or associated with Stability AI or any of its Affiliates, except as required under Section IV(a) herein.
+(ii)  Ownership of Derivative Works.  As between You and Stability AI, You are the owner of Derivative Works You create, subject to Stability AI’s ownership of the Stability AI Materials and any Derivative Works made by or for Stability AI.
+(iii)  Ownership of Outputs. As between You and Stability AI, You own any outputs generated from the Models or Derivative Works to the extent permitted by applicable law. 
+(iv)  Disputes.  If You or Your Affiliate(s) institute litigation or other proceedings against Stability AI (including a cross-claim or counterclaim in a lawsuit) alleging that the Stability AI Materials, Derivative Works or associated outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by You, then any licenses granted to You under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Stability AI from and against any claim by any third party arising out of or related to Your use or distribution of the Stability AI Materials or Derivative Works in violation of this Agreement.
+(v)  Feedback.  From time to time, You may provide Stability AI with verbal and/or written suggestions, comments or other feedback related to Stability AI’s existing or prospective technology, products or services (collectively, “Feedback”). You are not obligated to provide Stability AI with Feedback, but to the extent that You do, You hereby grant Stability AI a perpetual, irrevocable, royalty-free, fully-paid, sub-licensable, transferable, non-exclusive, worldwide right and license to exploit the Feedback in any manner without restriction. Your Feedback is provided “AS IS” and You make no warranties whatsoever about any Feedback.
+d.  Disclaimer Of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE STABILITY AI MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OR LAWFULNESS OF USING OR REDISTRIBUTING THE STABILITY AI MATERIALS, DERIVATIVE WORKS OR ANY OUTPUT OR RESULTS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE STABILITY AI MATERIALS, DERIVATIVE WORKS AND ANY OUTPUT AND RESULTS.
+e.  Limitation Of Liability. IN NO EVENT WILL STABILITY AI OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY DIRECT, INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF STABILITY AI OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+f.  Term And Termination. The term of this Agreement will commence upon Your acceptance of this Agreement or access to the Stability AI Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Stability AI may terminate this Agreement if You are in breach of any term or condition of this Agreement. Upon termination of this Agreement, You shall delete and cease use of any Stability AI Materials or Derivative Works. Section IV(d), (e), and (g) shall survive the termination of this Agreement.
+g.  Governing Law.  This Agreement will be governed by and constructed in accordance with the laws of the United States and the State of California without regard to choice of law principles, and the UN Convention on Contracts for International Sale of Goods does not apply to this Agreement.
+
+5. DEFINITIONS 
+
+“Affiliate(s)” means any entity that directly or indirectly controls, is controlled by, or is under common control with the subject entity; for purposes of this definition, “control” means direct or indirect ownership or control of more than 50% of the voting interests of the subject entity.
+
+"Agreement" means this Stability AI Community License Agreement.
+
+“AUP” means the Stability AI Acceptable Use Policy available at (https://stability.ai/use-policy), as may be updated from time to time.
+
+"Derivative Work(s)” means (a) any derivative work of the Stability AI Materials as recognized by U.S. copyright laws and (b) any modifications to a Model, and any other model created which is based on or derived from the Model or the Model’s output, including “fine tune” and “low-rank adaptation” models derived from a Model or a Model’s output, but do not include the output of any Model.
+
+“Documentation” means any specifications, manuals, documentation, and other written information provided by Stability AI related to the Software or Models.
+
+“Model(s)" means, collectively, Stability AI’s proprietary models and algorithms, including machine-learning models, trained model weights and other elements of the foregoing listed on Stability’s Core Models Webpage available at (https://stability.ai/core-models), as may be updated from time to time.
+
+"Stability AI" or "we" means Stability AI Ltd. and its Affiliates.
+
+"Software" means Stability AI’s proprietary software made available under this Agreement now or in the future.
+
+“Stability AI Materials” means, collectively, Stability’s proprietary Models, Software and Documentation (and any portion or combination thereof) made available under this Agreement. 
+
+“Trade Control Laws” means any applicable U.S. and non-U.S. export control and trade sanctions laws and regulations.

README.md

@@ -0,0 +1,175 @@
+---
+language:
+- en
+library_name: stable-audio-tools
+license: other
+license_name: stable-audio-community
+license_link: LICENSE
+pipeline_tag: text-to-audio
+extra_gated_prompt: By clicking "Agree", you agree to the [License Agreement](https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/LICENSE.md)
+  and acknowledge Stability AI's [Privacy Policy](https://stability.ai/privacy-policy).
+extra_gated_fields:
+  Name: text
+  Email: text
+  Country: country
+  Organization or Affiliation: text
+  Receive email updates and promotions on Stability AI products, services, and research?:
+    type: select
+    options:
+    - 'Yes'
+    - 'No'
+---
+
+# Stable Audio Open 1.0
+
+![Stable Audio Open logo](./stable_audio_light.png)
+
+Please note: For commercial use, please refer to [https://stability.ai/license](https://stability.ai/license)
+
+## Model Description
+`Stable Audio Open 1.0` generates variable-length (up to 47s) stereo audio at 44.1kHz from text prompts. It comprises three components: an autoencoder that compresses waveforms into a manageable sequence length, a T5-based text embedding for text conditioning, and a transformer-based diffusion (DiT) model that operates in the latent space of the autoencoder.
+
+## Usage
+
+This model can be used with:
+1. the [`stable-audio-tools`](https://github.com/Stability-AI/stable-audio-tools) library
+2. the [`diffusers`](https://huggingface.co/docs/diffusers/main/en/index) library
+
+
+### Using with `stable-audio-tools`
+
+This model is made to be used with the [`stable-audio-tools`](https://github.com/Stability-AI/stable-audio-tools) library for inference, for example:
+
+```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
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Download model
+model, model_config = get_pretrained_model("stabilityai/stable-audio-open-1.0")
+sample_rate = model_config["sample_rate"]
+sample_size = model_config["sample_size"]
+
+model = model.to(device)
+
+# Set up text and timing conditioning
+conditioning = [{
+    "prompt": "128 BPM tech house drum loop",
+    "seconds_start": 0, 
+    "seconds_total": 30
+}]
+
+# Generate stereo audio
+output = generate_diffusion_cond(
+    model,
+    steps=100,
+    cfg_scale=7,
+    conditioning=conditioning,
+    sample_size=sample_size,
+    sigma_min=0.3,
+    sigma_max=500,
+    sampler_type="dpmpp-3m-sde",
+    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)
+```
+
+## Using with `diffusers`
+
+Make sure you upgrade to the latest version of diffusers: `pip install -U diffusers`. And then you can run:
+
+```py
+import torch
+import soundfile as sf
+from diffusers import StableAudioPipeline
+
+pipe = StableAudioPipeline.from_pretrained("stabilityai/stable-audio-open-1.0", torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+# define the prompts
+prompt = "The sound of a hammer hitting a wooden surface."
+negative_prompt = "Low quality."
+
+# set the seed for generator
+generator = torch.Generator("cuda").manual_seed(0)
+
+# run the generation
+audio = pipe(
+    prompt,
+    negative_prompt=negative_prompt,
+    num_inference_steps=200,
+    audio_end_in_s=10.0,
+    num_waveforms_per_prompt=3,
+    generator=generator,
+).audios
+
+output = audio[0].T.float().cpu().numpy()
+sf.write("hammer.wav", output, pipe.vae.sampling_rate)
+
+```
+Refer to the [documentation](https://huggingface.co/docs/diffusers/main/en/index) for more details on optimization and usage.
+
+
+
+
+## Model Details
+* **Model type**: `Stable Audio Open 1.0` is a latent diffusion model based on a transformer architecture.
+* **Language(s)**: English
+* **License**: [Stability AI Community License](https://huggingface.co/stabilityai/stable-audio-open-1.0/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/2407.14358](https://arxiv.org/abs/2407.14358)
+
+## Training dataset
+
+### Datasets Used
+Our dataset consists of 486492 audio recordings, where 472618 are from Freesound and 13874 are from the Free Music Archive (FMA). All audio files are licensed under CC0, CC BY, or CC Sampling+. This data is used to train our autoencoder and DiT. We use a publicly available pre-trained T5 model ([t5-base](https://huggingface.co/google-t5/t5-base)) for text conditioning.
+
+### Attribution
+Attribution for all audio recordings used to train Stable Audio Open 1.0 can be found in this repository.
+- Freesound attribution [[csv](https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/freesound_dataset_attribution2.csv)]
+- FMA attribution [[csv](https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/fma_dataset_attribution2.csv)]
+
+### Mitigations
+We conducted an in-depth analysis to ensure no unauthorized copyrighted music was present in our training data before we began training.
+
+To that end, we first identified music samples in Freesound using the [PANNs](https://github.com/qiuqiangkong/audioset_tagging_cnn) music classifier based on AudioSet classes. The identified music samples had at least 30 seconds of music that was predicted to belong to a music-related class with a threshold of 0.15 (PANNs output probabilities range from 0 to 1). This threshold was determined by classifying known music examples from FMA and ensuring no false negatives were present. 
+
+The identified music samples were sent to Audible Magic’s identification services, a trusted content detection company, to ensure the absence of copyrighted music. Audible Magic flagged suspected copyrighted music, which we subsequently removed before training on the dataset. The majority of the removed content was field recordings in which copyrighted music was playing in the background. Following this procedure, we were left with 266324 CC0, 194840 CC-BY, and 11454 CC Sampling+ audio recordings.
+
+We also conducted an in-depth analysis to ensure no copyrighted content was present in FMA's subset. In this case, the procedure was slightly different because the FMA subset consists of music signals. We did a metadata search against a large database of copyrighted music (https://www.kaggle.com/datasets/maharshipandya/-spotify-tracks-dataset) and flagged any potential match. The flagged content was reviewed individually by humans. After this process, we ended up with 8967 CC-BY and 4907 CC0 tracks.
+
+
+## Use and Limitations
+
+
+### Intended Use
+The primary use of Stable Audio Open is research and experimentation on AI-based music and audio generation, including:
+
+- Research efforts to better understand the limitations of generative models and further improve the state of science.
+- Generation of music and audio guided by text to explore current abilities of generative AI models by machine learning practitioners and artists.
+
+
+### Out-of-Scope Use Cases
+The model should not be used on downstream applications without further risk evaluation and mitigation. The model should not be used to intentionally create or disseminate audio or music pieces that create hostile or alienating environments for people.
+
+
+### Limitations
+- The model is not able to generate realistic vocals.
+- The model has been trained with English descriptions and will not perform as well in other languages.
+- The model does not perform equally well for all music styles and cultures.
+- The model is better at generating sound effects and field recordings than music.
+- It is sometimes difficult to assess what types of text descriptions provide the best generations. Prompt engineering may be required to obtain satisfying results.
+
+
+### Biases
+The source of data is potentially lacking diversity and all cultures are not equally represented in the dataset. The model may not perform equally well on the wide variety of music genres and sound effects that exist. The generated samples from the model will reflect the biases from the training data.

freesound_dataset_attribution2.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8819b131646d3e48aa9e4571f7484c7a269bb9b639f2ce78a86e2cdefa5bb8eb
+size 50433223

model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73bf8bb7b6975483418813a954bca66471acac7a74e5f87d37774057bd82b504
+size 4164082314

model_config.json

@@ -0,0 +1,125 @@
+{
+    "model_type": "diffusion_cond",
+    "sample_size": 1048576,
+    "sample_rate": 44100,
+    "audio_channels": 2,
+    "model": {
+        "pretransform": {
+            "type": "autoencoder",
+            "iterate_batch": true,
+            "config": {
+                "encoder": {
+                    "type": "oobleck",
+                    "requires_grad": false,
+                    "config": {
+                        "in_channels": 2,
+                        "channels": 128,
+                        "c_mults": [1, 2, 4, 8, 16],
+                        "strides": [2, 4, 4, 8, 8],
+                        "latent_dim": 128,
+                        "use_snake": true
+                    }
+                },
+                "decoder": {
+                    "type": "oobleck",
+                    "config": {
+                        "out_channels": 2,
+                        "channels": 128,
+                        "c_mults": [1, 2, 4, 8, 16],
+                        "strides": [2, 4, 4, 8, 8],
+                        "latent_dim": 64,
+                        "use_snake": true,
+                        "final_tanh": false
+                    }
+                },
+                "bottleneck": {
+                    "type": "vae"
+                },
+                "latent_dim": 64,
+                "downsampling_ratio": 2048,
+                "io_channels": 2
+            }
+        },
+        "conditioning": {
+            "configs": [
+                {
+                    "id": "prompt",
+                    "type": "t5",
+                    "config": {
+                        "t5_model_name": "t5-base",
+                        "max_length": 128
+                    }
+                },
+                {
+                    "id": "seconds_start",
+                    "type": "number",
+                    "config": {
+                        "min_val": 0,
+                        "max_val": 512
+                    }
+                },
+                {
+                    "id": "seconds_total",
+                    "type": "number",
+                    "config": {
+                        "min_val": 0,
+                        "max_val": 512
+                    }
+                }
+            ],
+            "cond_dim": 768
+        },
+        "diffusion": {
+            "cross_attention_cond_ids": ["prompt", "seconds_start", "seconds_total"],
+            "global_cond_ids": ["seconds_start", "seconds_total"],
+            "type": "dit",
+            "config": {
+                "io_channels": 64,
+                "embed_dim": 1536,
+                "depth": 24,
+                "num_heads": 24,
+                "cond_token_dim": 768,
+                "global_cond_dim": 1536,
+                "project_cond_tokens": false,
+                "transformer_type": "continuous_transformer"
+            }
+        },
+        "io_channels": 64
+    },
+    "training": {
+        "use_ema": true,
+        "log_loss_info": false,
+        "optimizer_configs": {
+            "diffusion": {
+                "optimizer": {
+                    "type": "AdamW",
+                    "config": {
+                        "lr": 5e-5,
+                        "betas": [0.9, 0.999],
+                        "weight_decay": 1e-3
+                    }
+                },
+                "scheduler": {
+                    "type": "InverseLR",
+                    "config": {
+                        "inv_gamma": 1000000,
+                        "power": 0.5,
+                        "warmup": 0.99
+                    }
+                }
+            }
+        },
+        "demo": {
+            "demo_every": 2000,
+            "demo_steps": 250,
+            "num_demos": 4,
+            "demo_cond": [
+                {"prompt": "Amen break 174 BPM", "seconds_start": 0, "seconds_total": 12},
+                {"prompt": "A beautiful orchestral symphony, classical music", "seconds_start": 0, "seconds_total": 160},
+                {"prompt": "Chill hip-hop beat, chillhop", "seconds_start": 0, "seconds_total": 190},
+                {"prompt": "A pop song about love and loss", "seconds_start": 0, "seconds_total": 180}
+            ],
+            "demo_cfg_scales": [3, 6, 9]
+        }
+    }
+}

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "StableAudioPipeline",
+  "_diffusers_version": "0.30.0.dev0",
+  "projection_model": [
+    "stable_audio",
+    "StableAudioProjectionModel"
+  ],
+  "scheduler": [
+    "diffusers",
+    "CosineDPMSolverMultistepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "T5EncoderModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "T5TokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "StableAudioDiTModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderOobleck"
+  ]
+}

model_org.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6049ae92ec8362804cb4cb8a2845be93071439da2daff9997c285f8119d7ea40
+size 4853997287

projection_model/config.json

@@ -0,0 +1,8 @@
+{
+  "_class_name": "StableAudioProjectionModel",
+  "_diffusers_version": "0.30.0.dev0",
+  "conditioning_dim": 768,
+  "max_value": 512,
+  "min_value": 0,
+  "text_encoder_dim": 768
+}

projection_model/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032102e2b0e4b9b9e19c648dc476345157b97906752a7b4b7a0133900f340926
+size 1586944

scheduler/scheduler_config.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "CosineDPMSolverMultistepScheduler",
+  "_diffusers_version": "0.30.0.dev0",
+  "euler_at_final": false,
+  "final_sigmas_type": "zero",
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rho": 7.0,
+  "sigma_data": 1.0,
+  "sigma_max": 500,
+  "sigma_min": 0.3,
+  "sigma_schedule": "exponential",
+  "solver_order": 2,
+  "solver_type": "midpoint"
+}

text_encoder/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095878c81d21f17d235e1b4aa20e9595289177e2658ef4dcec69fa5aa3b07ca2
+size 438525864

tokenizer/special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer/tokenizer_config.json

@@ -0,0 +1,938 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 128,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "truncation": true,
+  "unk_token": "<unk>"
+}

transformer/config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "StableAudioDiTModel",
+  "_diffusers_version": "0.30.0.dev0",
+  "attention_head_dim": 64,
+  "cross_attention_dim": 768,
+  "cross_attention_input_dim": 768,
+  "global_states_input_dim": 1536,
+  "in_channels": 64,
+  "num_attention_heads": 24,
+  "num_key_value_attention_heads": 12,
+  "num_layers": 24,
+  "out_channels": 64,
+  "sample_size": 1024.0,
+  "time_proj_dim": 256
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ae9715febfeb2dc9f33aa506c2bda69fd2ddf8ebc483fb2df090df4ca506fd
+size 4227806200

vae/config.json

@@ -0,0 +1,23 @@
+{
+  "_class_name": "AutoencoderOobleck",
+  "_diffusers_version": "0.30.0.dev0",
+  "audio_channels": 2,
+  "channel_multiples": [
+    1,
+    2,
+    4,
+    8,
+    16
+  ],
+  "decoder_channels": 128,
+  "decoder_input_channels": 64,
+  "downsampling_ratios": [
+    2,
+    4,
+    4,
+    8,
+    8
+  ],
+  "encoder_hidden_size": 128,
+  "sampling_rate": 44100
+}

vae/diffusion_pytorch_model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4d46ad90feafc966011f7fd90a4a538b1f39c7d62b740fa99e95a2c1373aaa
+size 533824514

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2131cdb52020b2473707465449d8bdb4f6cca61c93150a947baca02bc58ffd7b
+size 624490240