openai
/

whisper-medium.en

Automatic Speech Recognition Transformers PyTorch TensorFlow JAX Safetensors English whisper audio hf-asr-leaderboard Eval Results Inference Endpoints

Model card Files Files and versions Community

ArthurZ HF staff commited on Sep 26, 2022

Commit

13d8f54

•

1 Parent(s): c6da634

Upload processor

Browse files

Files changed (6) hide show

added_tokens.json +108 -0
merges.txt +0 -0
preprocessor_config.json +0 -0
special_tokens_map.json +119 -0
tokenizer_config.json +35 -0
vocab.json +0 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,108 @@

+{
+  "<|af|>": 50326,
+  "<|am|>": 50333,
+  "<|ar|>": 50271,
+  "<|as|>": 50349,
+  "<|az|>": 50303,
+  "<|ba|>": 50354,
+  "<|be|>": 50329,
+  "<|bg|>": 50291,
+  "<|bn|>": 50301,
+  "<|bo|>": 50346,
+  "<|br|>": 50308,
+  "<|bs|>": 50314,
+  "<|ca|>": 50269,
+  "<|cs|>": 50282,
+  "<|cy|>": 50296,
+  "<|da|>": 50284,
+  "<|de|>": 50260,
+  "<|el|>": 50280,
+  "<|en|>": 50258,
+  "<|es|>": 50261,
+  "<|et|>": 50306,
+  "<|eu|>": 50309,
+  "<|fa|>": 50299,
+  "<|fi|>": 50276,
+  "<|fo|>": 50337,
+  "<|fr|>": 50264,
+  "<|gl|>": 50318,
+  "<|gu|>": 50332,
+  "<|haw|>": 50351,
+  "<|ha|>": 50353,
+  "<|hi|>": 50275,
+  "<|hr|>": 50290,
+  "<|ht|>": 50338,
+  "<|hu|>": 50285,
+  "<|hy|>": 50311,
+  "<|id|>": 50274,
+  "<|is|>": 50310,
+  "<|it|>": 50273,
+  "<|iw|>": 50278,
+  "<|ja|>": 50265,
+  "<|jw|>": 50355,
+  "<|ka|>": 50328,
+  "<|kk|>": 50315,
+  "<|km|>": 50322,
+  "<|kn|>": 50305,
+  "<|ko|>": 50263,
+  "<|la|>": 50293,
+  "<|lb|>": 50344,
+  "<|ln|>": 50352,
+  "<|lo|>": 50335,
+  "<|lt|>": 50292,
+  "<|lv|>": 50300,
+  "<|mg|>": 50348,
+  "<|mi|>": 50294,
+  "<|mk|>": 50307,
+  "<|ml|>": 50295,
+  "<|mn|>": 50313,
+  "<|mr|>": 50319,
+  "<|ms|>": 50281,
+  "<|mt|>": 50342,
+  "<|my|>": 50345,
+  "<|ne|>": 50312,
+  "<|nl|>": 50270,
+  "<|nn|>": 50341,
+  "<|nocaptions|>": 50361,
+  "<|notimestamps|>": 50362,
+  "<|no|>": 50287,
+  "<|oc|>": 50327,
+  "<|pa|>": 50320,
+  "<|pl|>": 50268,
+  "<|ps|>": 50339,
+  "<|pt|>": 50266,
+  "<|ro|>": 50283,
+  "<|ru|>": 50262,
+  "<|sa|>": 50343,
+  "<|sd|>": 50331,
+  "<|si|>": 50321,
+  "<|sk|>": 50297,
+  "<|sl|>": 50304,
+  "<|sn|>": 50323,
+  "<|so|>": 50325,
+  "<|sq|>": 50316,
+  "<|sr|>": 50302,
+  "<|startoflm|>": 50359,
+  "<|startofprev|>": 50360,
+  "<|startoftranscript|>": 50257,
+  "<|su|>": 50356,
+  "<|sv|>": 50272,
+  "<|sw|>": 50317,
+  "<|ta|>": 50286,
+  "<|te|>": 50298,
+  "<|tg|>": 50330,
+  "<|th|>": 50288,
+  "<|tk|>": 50340,
+  "<|tl|>": 50347,
+  "<|transcribe|>": 50358,
+  "<|translate|>": 50357,
+  "<|tr|>": 50267,
+  "<|tt|>": 50350,
+  "<|uk|>": 50279,
+  "<|ur|>": 50289,
+  "<|uz|>": 50336,
+  "<|vi|>": 50277,
+  "<|yi|>": 50334,
+  "<|yo|>": 50324,
+  "<|zh|>": 50259
+}

merges.txt ADDED Viewed

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

preprocessor_config.json ADDED Viewed

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

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,119 @@

+{
+  "additional_special_tokens": [
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|iw|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,35 @@

+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "/home/arthur_huggingface_co/transformers/whisper-any.en",
+  "pad_token": null,
+  "processor_class": "WhisperProcessor",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

vocab.json ADDED Viewed

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