Update config.json

config.json

@@ -4,29 +4,17 @@
   "activation_function": "gelu",
   "apply_spec_augment": false,
   "architectures": [
-    "WhisperEncoder"
+    "WhisperEncoderOnly"
   ],
   "attention_dropout": 0.0,
-  "begin_suppress_tokens": [
-    220,
-    50256
-  ],
-  "bos_token_id": 50256,
   "classifier_proj_size": 256,
   "d_model": 1280,
-  "decoder_attention_heads": 6,
-  "decoder_ffn_dim": 1536,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 4,
-  "decoder_start_token_id": 50257,
   "dropout": 0.0,
   "encoder_attention_heads": 20,
   "encoder_ffn_dim": 5120,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 32,
-  "eos_token_id": 50256,
   "init_std": 0.02,
-  "is_encoder_decoder": true,
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
@@ -35,16 +23,13 @@
   "mask_time_prob": 0.05,
   "max_length": 448,
   "max_source_positions": 1500,
-  "max_target_positions": 448,
   "median_filter_width": 7,
-  "model_type": "whisper",
+  "model_type": "whisper_encoder",
   "num_hidden_layers": 32,
   "num_mel_bins": 80,
-  "pad_token_id": 50256,
   "scale_embedding": false,
   "torch_dtype": "float32",
   "transformers_version": "4.44.0",
-  "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
-}
+}