Upload folder using huggingface_hub

Browse files

Files changed (8) hide show

config.json +5 -97
generation_config.json +4 -14
merges.txt +1 -0
model.safetensors +2 -2
preprocessor_config.json +1 -0
tokenizer.json +0 -0
tokenizer_config.json +1 -0
vocab.json +0 -0

config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "openai/whisper-small",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -7,10 +6,7 @@
     "WhisperForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
   "d_model": 768,
@@ -20,6 +16,7 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
@@ -47,7 +44,7 @@
   "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,
@@ -56,97 +53,8 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "suppress_tokens": [
-    1,
-    2,
-    7,
-    8,
-    9,
-    10,
-    14,
-    25,
-    26,
-    27,
-    28,
-    29,
-    31,
-    58,
-    59,
-    60,
-    61,
-    62,
-    63,
-    90,
-    91,
-    92,
-    93,
-    359,
-    503,
-    522,
-    542,
-    873,
-    893,
-    902,
-    918,
-    922,
-    931,
-    1350,
-    1853,
-    1982,
-    2460,
-    2627,
-    3246,
-    3253,
-    3268,
-    3536,
-    3846,
-    3961,
-    4183,
-    4667,
-    6585,
-    6647,
-    7273,
-    9061,
-    9383,
-    10428,
-    10929,
-    11938,
-    12033,
-    12331,
-    12562,
-    13793,
-    14157,
-    14635,
-    15265,
-    15618,
-    16553,
-    16604,
-    18362,
-    18956,
-    20075,
-    21675,
-    22520,
-    26130,
-    26161,
-    26435,
-    28279,
-    29464,
-    31650,
-    32302,
-    32470,
-    36865,
-    42863,
-    47425,
-    49870,
-    50254,
-    50258,
-    50360,
-    50361,
-    50362
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.37.0.dev0",
-  "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

 {
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
     "WhisperForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
   "d_model": 768,
   "decoder_layers": 12,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
+  "dtype": "float16",
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 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,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
+  "transformers_version": "4.57.2",
+  "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

generation_config.json CHANGED Viewed

@@ -48,16 +48,7 @@
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      null
-    ],
-    [
-      2,
-      50359
-    ]
-  ],
   "is_multilingual": true,
   "lang_to_id": {
     "<|af|>": 50327,
@@ -160,10 +151,11 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "max_initial_timestamp_index": 1,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
   "pad_token_id": 50257,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
@@ -249,8 +241,6 @@
     49870,
     50254,
     50258,
-    50358,
-    50359,
     50360,
     50361,
     50362
@@ -259,5 +249,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.37.0.dev0"
 }

   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
+  "forced_decoder_ids": null,
   "is_multilingual": true,
   "lang_to_id": {
     "<|af|>": 50327,
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
   "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
     49870,
     50254,
     50258,
     50360,
     50361,
     50362
     "transcribe": 50359,
     "translate": 50358
   },
+  "transformers_version": "4.57.2"
 }

merges.txt CHANGED Viewed

@@ -1,4 +1,5 @@
 #version: 0.2
 Ġ a
 Ġt h
 i n

 #version: 0.2
+Ġ t
 Ġ a
 Ġt h
 i n

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7adc3357fc00a2f66b4bc34b85c301d3366da5a2be1e008ea1d1fc872e39b8f
-size 966995080

 version https://git-lfs.github.com/spec/v1
+oid sha256:3684c3e1f2fe9d95334852e512906ae1121b3c569c04267250e55f1362342be7
+size 483525200

preprocessor_config.json CHANGED Viewed

@@ -1,5 +1,6 @@
 {
   "chunk_length": 30,
   "feature_extractor_type": "WhisperFeatureExtractor",
   "feature_size": 80,
   "hop_length": 160,

 {
   "chunk_length": 30,
+  "dither": 0.0,
   "feature_extractor_type": "WhisperFeatureExtractor",
   "feature_size": 80,
   "hop_length": 160,

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -12980,6 +12980,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
   "processor_class": "WhisperProcessor",

   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
   "processor_class": "WhisperProcessor",

vocab.json CHANGED Viewed

The diff for this file is too large to render. See raw diff