Model files, fixed

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-large-v3",
+  "_name_or_path": "openai/whisper-large-v3-turbo",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -9,7 +9,7 @@
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
     220,
-    50257
+    50256
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
@@ -17,7 +17,7 @@
   "decoder_attention_heads": 20,
   "decoder_ffn_dim": 5120,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 32,
+  "decoder_layers": 4,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
   "encoder_attention_heads": 20,
@@ -33,17 +33,16 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
-  "max_length": 448,
   "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,
+  "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.47.1",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51866

generation_config.json

@@ -1,5 +1,30 @@
 {
-  "alignment_heads": null,
+  "alignment_heads": [
+    [
+      2,
+      4
+    ],
+    [
+      2,
+      11
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      6
+    ],
+    [
+      3,
+      11
+    ],
+    [
+      3,
+      14
+    ]
+  ],
   "begin_suppress_tokens": [
     220,
     50257
@@ -14,7 +39,7 @@
     ],
     [
       2,
-      50359
+      50360
     ]
   ],
   "is_multilingual": true,
@@ -117,13 +142,14 @@
     "<|vi|>": 50278,
     "<|yi|>": 50335,
     "<|yo|>": 50325,
+    "<|yue|>": 50358,
     "<|zh|>": 50260
   },
   "max_initial_timestamp_index": 50,
   "max_length": 448,
-  "no_timestamps_token_id": 50363,
+  "no_timestamps_token_id": 50364,
   "pad_token_id": 50257,
-  "prev_sot_token_id": 50361,
+  "prev_sot_token_id": 50362,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
@@ -209,15 +235,15 @@
     49870,
     50254,
     50258,
-    50358,
     50359,
     50360,
     50361,
-    50362
+    50362,
+    50363
   ],
   "task_to_id": {
-    "transcribe": 50359,
-    "translate": 50358
+    "transcribe": 50360,
+    "translate": 50359
   },
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.47.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ef797c6dbb3256d71d68055f51074587e8b30e863b6e4be23fa77a293c14971
-size 3235581408
+oid sha256:1e096126d1f60b49040516e5c65719b5cadaa9c2113f961384e9b0790e04733f
+size 1750601920

tokenizer_config.json

@@ -12987,6 +12987,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
   "processor_class": "WhisperProcessor",