Upload config.json with huggingface_hub

config.json

@@ -1,62 +1,38 @@
 {
-    "model_type": "musicgen",
-    "text_encoder": {
-        "model_type": "t5",
-        "name_or_path": "t5-base",
-        "type": "T5EncoderModel",
-        "config": {
-            "vocab_size": 32128,
-            "d_model": 1024,
-            "num_layers": 12,
-            "num_heads": 16,
-            "dropout_rate": 0.1
-        }
-    },
-    "audio_encoder": {
-        "model_type": "wav2vec2",
-        "name_or_path": "facebook/wav2vec2-large",
-        "type": "AudioEncoder",
-        "config": {
-            "sample_rate": 32000,
-            "num_channels": 1,
-            "embedding_size": 512
-        }
-    },
-    "decoder": {
-        "model_type": "transformer",
-        "name_or_path": "facebook/musicgen-large",
-        "type": "TransformerDecoder",
-        "config": {
-            "d_model": 1024,
-            "num_heads": 16,
-            "num_layers": 24,
-            "dropout_rate": 0.1
-        }
-    },
-    "training": {
-        "batch_size": 16,
-        "num_epochs": 100,
-        "learning_rate": 0.0001,
-        "weight_decay": 0.01,
-        "gradient_clipping": 1.0
-    },
-    "generation": {
-        "sample_rate": 32000,
-        "audio_format": "wav",
-        "num_samples": 5,
-        "max_duration": 30.0,
-        "temperature": 1.0,
-        "top_k": 250,
-        "top_p": 0.9
-    },
-    "logging": {
-        "log_tensorboard": true,
-        "log_wandb": true,
-        "wandb_project": "music_generation",
-        "log_updates": 10
-    },
-    "hardware": {
-        "device": "cuda",
-        "num_gpus": 4
-    }
-}
+  "architectures": [
+    "EncodecModel"
+  ],
+  "audio_channels": 1,
+  "chunk_length_s": null,
+  "codebook_dim": 128,
+  "codebook_size": 2048,
+  "compress": 2,
+  "dilation_growth_rate": 2,
+  "hidden_size": 128,
+  "kernel_size": 7,
+  "last_kernel_size": 7,
+  "model_type": "encodec",
+  "norm_type": "weight_norm",
+  "normalize": false,
+  "num_filters": 64,
+  "num_lstm_layers": 2,
+  "num_residual_layers": 1,
+  "overlap": null,
+  "pad_mode": "reflect",
+  "residual_kernel_size": 3,
+  "sampling_rate": 32000,
+  "target_bandwidths": [
+    2.2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "trim_right_ratio": 1.0,
+  "upsampling_ratios": [
+    8,
+    5,
+    4,
+    4
+  ],
+  "use_causal_conv": false,
+  "use_conv_shortcut": false
+}