Upload 3 files

config.json

@@ -1,62 +1,61 @@
-## hugging face whisper config parameters can be ignored and are there for compatibility model should be loaded with initialization of model code for now
-{
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "apply_spec_augment": false,
-  "architectures": [
-    "Echo"
-  ],
-  "attention_dropout": 0.0,
-  "base": 10000,
-  "begin_suppress_tokens": [
-    220,
-    50256
-  ],
-  "bos_token_id": 50257,
-  "checkpointing": true,
-  "classifier_proj_size": 256,
-  "cross_attention": true,
-  "d_model": 384,
-  "decoder_attention_heads": 6,
-  "decoder_ffn_dim": 1536,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 4,
-  "decoder_start_token_id": 50258,
-  "dropout": 0.0,
-  "encoder_attention_heads": 6,
-  "encoder_ffn_dim": 1536,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 4,
-  "eos_token_id": 50257,
-  "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_rel_dist": 15,
-  "max_source_positions": 1500,
-  "max_target_positions": 448,
-  "median_filter_width": 7,
-  "model_type": "whisper",
-  "n_audio_ctx": 1500,
-  "n_audio_head": 16,
-  "n_audio_layer": 24,
-  "n_audio_state": 1024,
-  "n_mels": 80,
-  "n_text_ctx": 448,
-  "n_text_head": 16,
-  "n_text_layer": 20,
-  "n_text_state": 1024,
-  "num_hidden_layers": 4,
-  "num_mel_bins": 80,
-  "pad_token_id": 50257,
-  "scale_embedding": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.47.0",
-  "use_cache": true,
-  "use_weighted_layer_sum": false,
-  "vocab_size": 51865
-}
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "Echo"
+  ],
+  "attention_dropout": 0.0,
+  "base": 10000,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50257,
+  "checkpointing": true,
+  "classifier_proj_size": 256,
+  "cross_attention": true,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 50257,
+  "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_rel_dist": 200,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "n_audio_ctx": 1500,
+  "n_audio_head": 16,
+  "n_audio_layer": 24,
+  "n_audio_state": 1024,
+  "n_mels": 128,
+  "n_text_ctx": 448,
+  "n_text_head": 16,
+  "n_text_layer": 20,
+  "n_text_state": 1024,
+  "num_hidden_layers": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead546823f5ff3feaccdc9e6d236f78a407f7954cbf4f383e164d84499b528d1
-size 3204676144
+oid sha256:9c839a0eda6edd94c84d85a90d7746e9587b7261b038842741fa0ba3e86f111f
+size 3203825480