Upload TFWhisperForConditionalGeneration

README.md

@@ -14,12 +14,12 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5307
-- Train Accuracy: 0.0308
-- Train Wermet: 6.4113
-- Validation Loss: 0.6640
-- Validation Accuracy: 0.0306
-- Validation Wermet: 5.7589
+- Train Loss: 0.4694
+- Train Accuracy: 0.0303
+- Train Wermet: 4.3895
+- Validation Loss: 0.6038
+- Validation Accuracy: 0.0304
+- Validation Wermet: 2.8294
 - Epoch: 9
 
 ## Model description
@@ -46,21 +46,21 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
 |:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
-| 5.0860     | 0.0116         | 45.4352      | 4.4455          | 0.0124              | 36.1611           | 0     |
-| 4.3098     | 0.0131         | 29.4890      | 4.0321          | 0.0144              | 24.9514           | 1     |
-| 3.6711     | 0.0160         | 25.7380      | 2.7995          | 0.0205              | 32.2126           | 2     |
-| 2.2582     | 0.0224         | 31.5946      | 1.6772          | 0.0257              | 23.9282           | 3     |
-| 1.4268     | 0.0262         | 23.3380      | 1.2097          | 0.0279              | 18.7331           | 4     |
-| 1.0613     | 0.0279         | 13.6764      | 0.9972          | 0.0289              | 10.7707           | 5     |
-| 0.8545     | 0.0290         | 9.2746       | 0.8605          | 0.0296              | 6.5566            | 6     |
-| 0.7144     | 0.0297         | 7.4723       | 0.7768          | 0.0300              | 5.4825            | 7     |
-| 0.6116     | 0.0303         | 6.9092       | 0.7125          | 0.0304              | 6.5220            | 8     |
-| 0.5307     | 0.0308         | 6.4113       | 0.6640          | 0.0306              | 5.7589            | 9     |
+| 5.0729     | 0.0113         | 42.1824      | 4.4421          | 0.0120              | 27.3059           | 0     |
+| 4.3249     | 0.0126         | 23.9224      | 4.0443          | 0.0141              | 18.2054           | 1     |
+| 3.8845     | 0.0144         | 12.7780      | 3.4577          | 0.0169              | 10.3356           | 2     |
+| 2.7411     | 0.0198         | 15.0018      | 1.8774          | 0.0244              | 14.5666           | 3     |
+| 1.5621     | 0.0250         | 9.7248       | 1.2443          | 0.0273              | 5.4731            | 4     |
+| 1.0745     | 0.0272         | 7.1512       | 0.9802          | 0.0285              | 4.4745            | 5     |
+| 0.8261     | 0.0284         | 6.2358       | 0.8209          | 0.0293              | 5.6600            | 6     |
+| 0.6673     | 0.0292         | 5.8338       | 0.7182          | 0.0298              | 4.0874            | 7     |
+| 0.5548     | 0.0298         | 5.0555       | 0.6489          | 0.0301              | 4.4537            | 8     |
+| 0.4694     | 0.0303         | 4.3895       | 0.6038          | 0.0304              | 2.8294            | 9     |
 
 
 ### Framework versions
 
-- Transformers 4.25.0.dev0
-- TensorFlow 2.9.2
-- Datasets 2.6.1
+- Transformers 4.27.0.dev0
+- TensorFlow 2.11.0
+- Datasets 2.10.0
 - Tokenizers 0.13.2

config.json

@@ -2,6 +2,7 @@
   "_name_or_path": "openai/whisper-tiny",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
+  "apply_spec_augment": false,
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
@@ -26,6 +27,12 @@
   "forced_decoder_ids": null,
   "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_length": 448,
   "max_source_positions": 1500,
   "max_target_positions": 448,
@@ -36,7 +43,7 @@
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.25.0.dev0",
+  "transformers_version": "4.27.0.dev0",
   "use_cache": true,
   "vocab_size": 51865
 }

generation_config.json

@@ -0,0 +1,219 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "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,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 1,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50256,
+  "return_timestamps": 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
+  ],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.27.0.dev0"
+}

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c561da382ea962808b88bcfe367b175f117430f8280bfb5d0e28d5ba4b17ef
+oid sha256:99dd90a3d2fcc98b12dd931f20fa47abe73b886d99c4d2b79ceecb8eef1dd4c7
 size 151253984