Upload TFWhisperForConditionalGeneration

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: whisper_new_split_0035
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# whisper_new_split_0035
+
+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: 0.0054
+- Train Accuracy: 0.0335
+- Train Wermet: 27.4530
+- Validation Loss: 0.4807
+- Validation Accuracy: 0.0315
+- Validation Wermet: 30.3598
+- Epoch: 34
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
+|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
+| 5.1027     | 0.0113         | 52.5530      | 4.4267          | 0.0121              | 41.4796           | 0     |
+| 4.3285     | 0.0126         | 38.6893      | 3.9835          | 0.0145              | 33.6050           | 1     |
+| 3.4573     | 0.0168         | 30.7714      | 2.5568          | 0.0215              | 31.7559           | 2     |
+| 2.0878     | 0.0226         | 20.5131      | 1.5738          | 0.0257              | 21.2159           | 3     |
+| 1.3529     | 0.0258         | 17.4367      | 1.1712          | 0.0276              | 17.7695           | 4     |
+| 0.9953     | 0.0275         | 18.7308      | 0.9389          | 0.0287              | 20.5259           | 5     |
+| 0.7852     | 0.0286         | 18.5731      | 0.8074          | 0.0294              | 17.6576           | 6     |
+| 0.6428     | 0.0293         | 18.2945      | 0.7219          | 0.0298              | 19.9850           | 7     |
+| 0.5384     | 0.0299         | 18.9258      | 0.6610          | 0.0301              | 18.9327           | 8     |
+| 0.4565     | 0.0304         | 19.0749      | 0.6117          | 0.0304              | 21.9796           | 9     |
+| 0.3901     | 0.0308         | 19.2099      | 0.5693          | 0.0306              | 18.0965           | 10    |
+| 0.3348     | 0.0312         | 20.4777      | 0.5449          | 0.0307              | 19.9518           | 11    |
+| 0.2877     | 0.0315         | 20.3181      | 0.5232          | 0.0309              | 20.4017           | 12    |
+| 0.2471     | 0.0318         | 19.2073      | 0.5057          | 0.0310              | 18.7612           | 13    |
+| 0.2120     | 0.0320         | 19.0961      | 0.4925          | 0.0311              | 22.3187           | 14    |
+| 0.1809     | 0.0323         | 20.7944      | 0.4849          | 0.0311              | 27.2314           | 15    |
+| 0.1539     | 0.0325         | 22.0951      | 0.4787          | 0.0312              | 25.2171           | 16    |
+| 0.1299     | 0.0327         | 22.7652      | 0.4733          | 0.0312              | 22.7492           | 17    |
+| 0.1087     | 0.0329         | 25.2223      | 0.4701          | 0.0312              | 28.9044           | 18    |
+| 0.0899     | 0.0330         | 24.8354      | 0.4715          | 0.0313              | 21.1618           | 19    |
+| 0.0739     | 0.0332         | 25.4987      | 0.4680          | 0.0313              | 29.6304           | 20    |
+| 0.0604     | 0.0333         | 27.6465      | 0.4693          | 0.0313              | 27.6937           | 21    |
+| 0.0498     | 0.0333         | 27.7045      | 0.4711          | 0.0313              | 27.5013           | 22    |
+| 0.0414     | 0.0334         | 28.0547      | 0.4689          | 0.0313              | 29.1776           | 23    |
+| 0.0327     | 0.0334         | 27.5594      | 0.4718          | 0.0313              | 31.5623           | 24    |
+| 0.0256     | 0.0335         | 27.3983      | 0.4710          | 0.0313              | 27.1071           | 25    |
+| 0.0210     | 0.0335         | 24.7398      | 0.4736          | 0.0313              | 30.8282           | 26    |
+| 0.0165     | 0.0335         | 25.1927      | 0.4773          | 0.0313              | 24.1750           | 27    |
+| 0.0133     | 0.0335         | 25.6261      | 0.4807          | 0.0313              | 29.9520           | 28    |
+| 0.0110     | 0.0335         | 25.8127      | 0.4825          | 0.0314              | 27.0813           | 29    |
+| 0.0171     | 0.0335         | 26.0445      | 0.4858          | 0.0313              | 39.8503           | 30    |
+| 0.0154     | 0.0335         | 28.6186      | 0.4766          | 0.0314              | 28.4465           | 31    |
+| 0.0094     | 0.0335         | 27.8978      | 0.4778          | 0.0314              | 28.7775           | 32    |
+| 0.0071     | 0.0335         | 27.8180      | 0.4775          | 0.0314              | 28.5229           | 33    |
+| 0.0054     | 0.0335         | 27.4530      | 0.4807          | 0.0315              | 30.3598           | 34    |
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- TensorFlow 2.11.0
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "openai/whisper-tiny",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    50257
+  ],
+  "bos_token_id": 50257,
+  "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,
+  "forced_decoder_ids": [
+    [
+      1,
+      50289
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "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,
+  "model_type": "whisper",
+  "num_hidden_layers": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8941fb4d52e743e8f270fad5e98c544d18f9202ec7aed31202deb787835d89
+size 151253984