Preserve model config as config.json

config.json

@@ -1 +1,47 @@
-{"model_type": "whisper", "features_size": 80, "subsampling_factor": 8, "max_tokens_per_step": 10}
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

model-config.json

@@ -1,47 +0,0 @@
-{
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "apply_spec_augment": false,
-  "architectures": [
-    "WhisperForConditionalGeneration"
-  ],
-  "attention_dropout": 0.0,
-  "begin_suppress_tokens": null,
-  "bos_token_id": 50257,
-  "classifier_proj_size": 256,
-  "d_model": 1280,
-  "decoder_attention_heads": 20,
-  "decoder_ffn_dim": 5120,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 32,
-  "decoder_start_token_id": 50258,
-  "dropout": 0.0,
-  "dtype": "float32",
-  "encoder_attention_heads": 20,
-  "encoder_ffn_dim": 5120,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 32,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": null,
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "mask_feature_length": 10,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.0,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_prob": 0.05,
-  "max_length": null,
-  "max_source_positions": 1500,
-  "max_target_positions": 448,
-  "median_filter_width": 7,
-  "model_type": "whisper",
-  "num_hidden_layers": 32,
-  "num_mel_bins": 128,
-  "pad_token_id": 50256,
-  "scale_embedding": false,
-  "transformers_version": "4.57.6",
-  "use_cache": true,
-  "use_weighted_layer_sum": false,
-  "vocab_size": 51866
-}