Upload StableDiffusionCLAPPipeline

audio_encoder/config.json

@@ -1,29 +1,49 @@
 {
   "_name_or_path": "dhuck/stable-diffusion-clap/audio_encoder",
+  "aff_block_r": 4,
   "architectures": [
-    "ClapModel"
+    "ClapAudioModel"
   ],
-  "audio_config": {
-    "depths": [
-      2,
-      2,
-      12,
-      2
-    ],
-    "hidden_size": 1024,
-    "model_type": "clap_audio_model",
-    "patch_embeds_hidden_size": 128
-  },
-  "hidden_size": 768,
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    12,
+    2
+  ],
+  "drop_path_rate": 0.0,
+  "enable_fusion": false,
+  "enable_patch_layer_norm": true,
+  "flatten_patch_embeds": true,
+  "fusion_type": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "initializer_factor": 1.0,
-  "logit_scale_init_value": 14.285714285714285,
-  "model_type": "clap",
-  "num_hidden_layers": 16,
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "clap_audio_model",
+  "num_attention_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "num_classes": 527,
+  "num_hidden_layers": 4,
+  "num_mel_bins": 64,
+  "patch_embed_input_channels": 1,
+  "patch_embeds_hidden_size": 128,
+  "patch_size": 4,
+  "patch_stride": [
+    4,
+    4
+  ],
   "projection_dim": 512,
   "projection_hidden_act": "relu",
-  "text_config": {
-    "model_type": "clap_text_model"
-  },
+  "qkv_bias": true,
+  "spec_size": 256,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.1"
+  "transformers_version": "4.37.1",
+  "window_size": 8
 }

audio_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013f1d40b8981b5dd741c0ccc444ae6cf8485d7cd4333892bcb2c6e8c3047064
-size 776327440
+oid sha256:0542c0ea071de5a84232c0394c42c9ffffc6dd422e0a364685ade6021172888d
+size 271931456

audio_processor/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

audio_processor/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "ClapProcessor",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

model_index.json

@@ -4,11 +4,11 @@
   "_name_or_path": "dhuck/stable-diffusion-clap",
   "audio_encoder": [
     "transformers",
-    "ClapModel"
+    "ClapAudioModel"
   ],
   "audio_processor": [
     "transformers",
-    "ClapFeatureExtractor"
+    "ClapProcessor"
   ],
   "feature_extractor": [
     "transformers",

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4b34e16d5d66b2e6f2fada83896128d02371a549943c84e5effc0df67825c2
+oid sha256:90c904a46af0e172d59ee379709f77cf2e53012706c4935bd73e4593d672132e
 size 3509909336