Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "laion/larger_clap_music_and_speech",
+  "architectures": [
+    "ClapModel"
+  ],
+  "audio_config": {
+    "depths": [
+      2,
+      2,
+      12,
+      2
+    ],
+    "hidden_size": 1024,
+    "model_type": "clap_audio_model",
+    "patch_embeds_hidden_size": 128
+  },
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 14.285714285714285,
+  "model_type": "clap",
+  "num_hidden_layers": 16,
+  "projection_dim": 512,
+  "projection_hidden_act": "relu",
+  "text_config": {
+    "model_type": "clap_text_model"
+  },
+  "transformers_version": "4.36.0.dev0"
+}

onnx/audio_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ecc72d27740e2a09ced20cf22fd6244122e5e506008763a0f368b3b4ff6eac8
+size 281749092

onnx/audio_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021dd4fb962b4ed20cc3a6730b09e0ccf9f9c49931047032118a3b64828513a6
+size 78155433

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d04513d60208d79789a494669a78fc85c4b11a3593a04e3bc2ddac3d48af46
+size 783395985

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1118620d1f8c0585e8aff047f5ca464f6b4618dafa0422b4125a7f4beb05f191
+size 204941195

onnx/text_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c0f248bfaabe5d467958245beb0243e387ed628251e3b407b856848379e89c
+size 501513769

onnx/text_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9f29c5f6adee917553d4b3a70729c731c0d18b88efca0ae67c1a1fc278f3b6
+size 126603262

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "chunk_length_s": 10,
+  "feature_extractor_type": "ClapFeatureExtractor",
+  "feature_size": 64,
+  "fft_window_size": 1024,
+  "frequency_max": 14000,
+  "frequency_min": 50,
+  "hop_length": 480,
+  "max_length_s": 10,
+  "n_fft": 1024,
+  "nb_frequency_bins": 513,
+  "nb_max_frames": 1000,
+  "nb_max_samples": 480000,
+  "padding": "repeatpad",
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "ClapProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 48000,
+  "top_db": null,
+  "truncation": "rand_trunc"
+}

quantize_config.json

@@ -0,0 +1,123 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "ConstantOfShape",
+                "Unsqueeze",
+                "Conv",
+                "Pow",
+                "Cast",
+                "Resize",
+                "ReduceMean",
+                "Sub",
+                "Mul",
+                "Constant",
+                "Slice",
+                "Not",
+                "Shape",
+                "Concat",
+                "Range",
+                "BatchNormalization",
+                "ScatterND",
+                "Where",
+                "Gather",
+                "Expand",
+                "Tanh",
+                "Identity",
+                "ReduceSum",
+                "Relu",
+                "Gemm",
+                "Sqrt",
+                "Equal",
+                "Erf",
+                "MatMul",
+                "Transpose",
+                "Exp",
+                "Add",
+                "Flatten",
+                "Abs",
+                "Softmax",
+                "CumSum",
+                "Div",
+                "Pad",
+                "Reshape",
+                "GlobalAveragePool"
+            ],
+            "weight_type": "QUInt8"
+        },
+        "text_model": {
+            "op_types": [
+                "Equal",
+                "Add",
+                "Slice",
+                "Cast",
+                "Tanh",
+                "Gather",
+                "Relu",
+                "Shape",
+                "MatMul",
+                "Softmax",
+                "Pow",
+                "CumSum",
+                "Erf",
+                "Div",
+                "Constant",
+                "ConstantOfShape",
+                "Not",
+                "Sqrt",
+                "Gemm",
+                "Reshape",
+                "Unsqueeze",
+                "Sub",
+                "ReduceMean",
+                "Where",
+                "Concat",
+                "Transpose",
+                "Mul",
+                "Expand"
+            ],
+            "weight_type": "QInt8"
+        },
+        "audio_model": {
+            "op_types": [
+                "Equal",
+                "GlobalAveragePool",
+                "Add",
+                "Conv",
+                "Slice",
+                "Resize",
+                "Cast",
+                "Gather",
+                "Range",
+                "Relu",
+                "ScatterND",
+                "Shape",
+                "MatMul",
+                "Softmax",
+                "Pow",
+                "Erf",
+                "Div",
+                "Constant",
+                "BatchNormalization",
+                "ConstantOfShape",
+                "Not",
+                "Sqrt",
+                "Gemm",
+                "Reshape",
+                "Pad",
+                "Unsqueeze",
+                "Flatten",
+                "ReduceMean",
+                "Sub",
+                "Where",
+                "Transpose",
+                "Concat",
+                "Mul",
+                "Expand"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "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,
+  "trust_remote_code": false,
+  "unk_token": "<unk>"
+}