Upload TFWhisperForConditionalGeneration

README.md

@@ -0,0 +1,91 @@
+---
+license: apache-2.0
+base_model: openai/whisper-tiny
+tags:
+- generated_from_keras_callback
+model-index:
+- name: whisper_charsplit_new_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_charsplit_new_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: 0.0130
+- Train Accuracy: 0.0793
+- Train Wermet: 11.1022
+- Validation Loss: 0.4748
+- Validation Accuracy: 0.0760
+- Validation Wermet: 9.4521
+- 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 |
+|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
+| 0.8733     | 0.0602         | 13.0686      | 0.6470          | 0.0676              | 11.4066           | 0     |
+| 0.5740     | 0.0666         | 12.7778      | 0.5113          | 0.0706              | 11.1022           | 1     |
+| 0.4553     | 0.0692         | 12.2404      | 0.4371          | 0.0723              | 10.9105           | 2     |
+| 0.3813     | 0.0708         | 11.9157      | 0.3935          | 0.0733              | 9.4615            | 3     |
+| 0.3292     | 0.0720         | 11.5732      | 0.3630          | 0.0740              | 9.9885            | 4     |
+| 0.2886     | 0.0729         | 11.5171      | 0.3403          | 0.0745              | 9.8042            | 5     |
+| 0.2561     | 0.0736         | 11.3173      | 0.3256          | 0.0749              | 9.9431            | 6     |
+| 0.2282     | 0.0743         | 11.7308      | 0.3159          | 0.0752              | 9.2086            | 7     |
+| 0.2036     | 0.0748         | 11.4503      | 0.3071          | 0.0754              | 9.5236            | 8     |
+| 0.1820     | 0.0754         | 11.7175      | 0.3005          | 0.0756              | 10.0755           | 9     |
+| 0.1628     | 0.0758         | 11.7056      | 0.2993          | 0.0757              | 9.9497            | 10    |
+| 0.1450     | 0.0762         | 11.7637      | 0.2971          | 0.0758              | 10.1481           | 11    |
+| 0.1287     | 0.0766         | 11.8509      | 0.3029          | 0.0759              | 10.2042           | 12    |
+| 0.1140     | 0.0770         | 12.1100      | 0.3004          | 0.0760              | 10.3873           | 13    |
+| 0.0998     | 0.0773         | 11.9502      | 0.3025          | 0.0761              | 10.7066           | 14    |
+| 0.0872     | 0.0777         | 12.3196      | 0.3129          | 0.0759              | 10.7707           | 15    |
+| 0.0760     | 0.0779         | 12.2637      | 0.3142          | 0.0761              | 10.2638           | 16    |
+| 0.0651     | 0.0782         | 12.1215      | 0.3192          | 0.0761              | 10.0750           | 17    |
+| 0.0547     | 0.0785         | 12.0551      | 0.3294          | 0.0761              | 10.4732           | 18    |
+| 0.0463     | 0.0787         | 11.9677      | 0.3402          | 0.0760              | 10.2814           | 19    |
+| 0.0386     | 0.0789         | 11.6855      | 0.3517          | 0.0760              | 10.0599           | 20    |
+| 0.0318     | 0.0790         | 11.6314      | 0.3628          | 0.0760              | 9.6652            | 21    |
+| 0.0262     | 0.0792         | 11.4603      | 0.3728          | 0.0760              | 10.0035           | 22    |
+| 0.0224     | 0.0792         | 11.4330      | 0.3824          | 0.0760              | 9.1995            | 23    |
+| 0.0181     | 0.0793         | 11.3124      | 0.3982          | 0.0759              | 9.8710            | 24    |
+| 0.0142     | 0.0794         | 11.3562      | 0.4057          | 0.0760              | 9.6831            | 25    |
+| 0.0118     | 0.0794         | 11.0532      | 0.4207          | 0.0759              | 9.7227            | 26    |
+| 0.0101     | 0.0794         | 11.2963      | 0.4282          | 0.0760              | 9.5792            | 27    |
+| 0.0114     | 0.0794         | 11.3093      | 0.4431          | 0.0758              | 9.5545            | 28    |
+| 0.0109     | 0.0794         | 11.4214      | 0.4419          | 0.0760              | 9.4377            | 29    |
+| 0.0084     | 0.0794         | 10.9143      | 0.4474          | 0.0760              | 9.3668            | 30    |
+| 0.0043     | 0.0795         | 10.9497      | 0.4525          | 0.0761              | 9.3202            | 31    |
+| 0.0036     | 0.0795         | 10.7759      | 0.4667          | 0.0761              | 9.0385            | 32    |
+| 0.0047     | 0.0795         | 10.7613      | 0.4788          | 0.0759              | 9.4065            | 33    |
+| 0.0130     | 0.0793         | 11.1022      | 0.4748          | 0.0760              | 9.4521            | 34    |
+
+
+### Framework versions
+
+- Transformers 4.32.0.dev0
+- TensorFlow 2.12.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,64 @@
+{
+  "_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,
+  "classifier_proj_size": 256,
+  "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,
+  "median_filter_width": 7,
+  "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": "4.32.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,117 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "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,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "transformers_version": "4.32.0.dev0"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa32d64f7907de36125c22f40cd35b85da76976c11fab85b5be0b718948d7923
+size 151253960