first commit

README.md

@@ -1,3 +1,91 @@
 ---
 license: cc-by-nc-sa-4.0
+datasets:
+- AudioCaps+others
+language:
+- en
+tags:
+- audio
 ---
+# 
+
+**Auffusion** is a latent diffusion model (LDM) for text-to-audio (TTA) generation. **Auffusion** can generate realistic audios including human sounds, animal sounds, natural and artificial sounds and sound effects from textual prompts. We introduce Auffusion, a TTA system adapting T2I model frameworks to TTA task, by effectively leveraging their inherent generative strengths and precise cross-modal alignment. Our objective and subjective evaluations demonstrate that Auffusion surpasses previous TTA approaches using limited data and computational resource. We release our model, inference code, and pre-trained checkpoints for the research community.
+
+📣 We are releasing **Auffusion-Full-no-adapter** which was pre-trained on all datasets described in paper and created for easy use of audio manipulation.
+📣 We are releasing **Auffusion-Full** which was pre-trained on all datasets described in paper.
+📣 We are releasing **Auffusion** which was pre-trained on **AudioCaps**.
+
+## Auffusion Model Family
+
+| Model Name                 | Model Path                                                                                                              |
+|----------------------------|------------------------------------------------------------------------------------------------------------------------ |
+| Auffusion                  | [https://huggingface.co/auffusion/auffusion](https://huggingface.co/auffusion/auffusion)                                |
+| Auffusion-Full             | [https://huggingface.co/auffusion/auffusion-full](https://huggingface.co/auffusion/auffusion-full)                      |
+| Auffusion-Full-no-adapter  | [https://huggingface.co/auffusion/auffusion-full-no-adapter](https://huggingface.co/auffusion/auffusion-full-no-adapter)|
+
+
+## Code
+
+Our code is released here: [https://github.com/happylittlecat2333/Auffusion](https://github.com/happylittlecat2333/Auffusion)
+
+We uploaded several **Auffusion** generated samples here: [https://auffusion.github.io](https://auffusion.github.io)
+
+Please follow the instructions in the repository for installation, usage and experiments.
+
+
+## Quickstart Guide
+
+We try to make **Auffusion-Full-no-adapter** compatible with text-to-image pipeline, therefore diffusers pipeline including StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, StableDiffusionInpaintPipeline etc. can be adapted. Other audio manipulation examples can be seen in [https://github.com/happylittlecat2333/Auffusion/notebooks](https://github.com/happylittlecat2333/Auffusion/notebooks). We only show the default text-to-audio example here.
+
+
+First, git clone the repository and install the requirements:
+
+```bash
+git clone https://github.com/happylittlecat2333/Auffusion/
+cd Auffusion
+pip install -r requirements.txt
+```
+
+Then, download the **Auffusion-Full-no-adapter** model and generate audio from a text prompt:
+
+```python
+import IPython, torch, os
+import soundfile as sf
+from diffusers import StableDiffusionPipeline
+from huggingface_hub import snapshot_download
+from converter import Generator, denormalize_spectrogram
+
+cuda = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.float16
+
+prompt = "A kitten mewing for attention"
+seed = 42
+
+pretrained_model_name_or_path = "auffusion/auffusion-full-no-adapter"
+if not os.path.isdir(pretrained_model_name_or_path):
+    pretrained_model_name_or_path = snapshot_download(pretrained_model_name_or_path) 
+
+vocoder = Generator.from_pretrained(pretrained_model_name_or_path, subfolder="vocoder")
+vocoder = vocoder.to(device=device, dtype=dtype)
+
+pipe = StableDiffusionPipeline.from_pretrained(pretrained_model_name_or_path, torch_dtype=dtype)
+pipe = pipe.to(device)
+
+generator = torch.Generator(device=device).manual_seed(seed)
+
+with torch.autocast("cuda"):
+    output_spec = pipe(
+        prompt=prompt, num_inference_steps=100, generator=generator, height=256, width=1024, output_type="pt"
+    ).images[0] # important to set output_type="pt" to get torch tensor output, and set height=256 with width=1024
+
+
+denorm_spec = denormalize_spectrogram(output_spec)
+denorm_spec_audio = vocoder.inference(denorm_spec)
+
+sf.write(f"{prompt}.wav", audio, samplerate=16000)
+IPython.display.Audio(data=audio, rate=16000)
+```
+
+The auffusion model will be automatically downloaded from huggingface and saved in cache. Subsequent runs will load the model directly from cache.
+
+Other audio manipulation examples can be seen in [https://github.com/happylittlecat2333/Auffusion/notebooks](https://github.com/happylittlecat2333/Auffusion/notebooks). We only show the default text-to-audio example here.

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.18.2",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": false,
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.18.2",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a536a73223d0aad893fd29e3b6095ac9b71ba6dafcb799c88f0abb4f173931f
+size 492306077

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,71 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.18.2",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "decay": 0.9999,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "inv_gamma": 1.0,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "min_decay": 0.0,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "optimization_step": 100000,
+  "out_channels": 4,
+  "power": 0.6666666666666666,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec9cfd445b979491261a5dc3e8df6984e00d13bec11ba477d1f08e39db06448
+size 3438366373

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.18.2",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02e0c7c263a4c0630ca3a72380ff55b9e38e0ab41d64dff7bf620a58342bc75
+size 334712113

vocoder/config.json

@@ -0,0 +1,37 @@
+{
+    "resblock": "1",
+    "num_gpus": 0,
+    "batch_size": 16,
+    "learning_rate": 0.0002,
+    "adam_b1": 0.8,
+    "adam_b2": 0.99,
+    "lr_decay": 0.999,
+    "seed": 1234,
+
+    "upsample_rates": [5,4,4,2],
+    "upsample_kernel_sizes": [11,8,8,4],
+    "upsample_initial_channel": 512,
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+
+    "segment_size": 5120,
+    "num_mels": 256,
+    "num_freq": 2049,
+    "n_fft": 2048,
+    "hop_size": 160,
+    "win_size": 1024,
+
+    "sampling_rate": 16000,
+
+    "fmin": 0,
+    "fmax": null,
+    "fmax_for_loss": null,
+
+    "num_workers": 4,
+
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "tcp://localhost:54321",
+        "world_size": 1
+    }
+}

vocoder/vocoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71bb8ec87c21902175cb0f918e739789ec085663ed0f8ebd2f20adba4d5b5af
+size 54808625