Upload TFWhisperForConditionalGeneration

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: whisper_final_09
+  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_final_09
+
+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: 0.0816
+- Train Accuracy: 0.0343
+- Validation Loss: 0.5877
+- Validation Accuracy: 0.0313
+- Epoch: 24
+
+## 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 | Validation Loss | Validation Accuracy | Epoch |
+|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
+| 5.0832     | 0.0116         | 4.4298          | 0.0124              | 0     |
+| 4.3130     | 0.0131         | 4.0733          | 0.0141              | 1     |
+| 3.9211     | 0.0146         | 3.6762          | 0.0157              | 2     |
+| 3.5505     | 0.0159         | 3.3453          | 0.0171              | 3     |
+| 3.1592     | 0.0175         | 2.8062          | 0.0199              | 4     |
+| 2.2581     | 0.0220         | 1.7622          | 0.0252              | 5     |
+| 1.4671     | 0.0259         | 1.2711          | 0.0276              | 6     |
+| 1.0779     | 0.0278         | 1.0220          | 0.0288              | 7     |
+| 0.8591     | 0.0290         | 0.8836          | 0.0295              | 8     |
+| 0.7159     | 0.0297         | 0.7918          | 0.0300              | 9     |
+| 0.6105     | 0.0304         | 0.7276          | 0.0303              | 10    |
+| 0.5287     | 0.0309         | 0.6850          | 0.0306              | 11    |
+| 0.4614     | 0.0313         | 0.6472          | 0.0308              | 12    |
+| 0.4049     | 0.0317         | 0.6199          | 0.0310              | 13    |
+| 0.3562     | 0.0320         | 0.6019          | 0.0311              | 14    |
+| 0.3139     | 0.0324         | 0.5868          | 0.0311              | 15    |
+| 0.2766     | 0.0326         | 0.5751          | 0.0312              | 16    |
+| 0.2438     | 0.0329         | 0.5701          | 0.0312              | 17    |
+| 0.2116     | 0.0332         | 0.5686          | 0.0313              | 18    |
+| 0.1844     | 0.0334         | 0.5619          | 0.0313              | 19    |
+| 0.1593     | 0.0336         | 0.5710          | 0.0313              | 20    |
+| 0.1363     | 0.0338         | 0.5656          | 0.0314              | 21    |
+| 0.1160     | 0.0340         | 0.5763          | 0.0313              | 22    |
+| 0.0981     | 0.0341         | 0.5806          | 0.0313              | 23    |
+| 0.0816     | 0.0343         | 0.5877          | 0.0313              | 24    |
+
+
+### Framework versions
+
+- Transformers 4.25.0.dev0
+- TensorFlow 2.9.2
+- Datasets 2.6.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,144 @@
+{
+  "_name_or_path": "openai/whisper-tiny",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    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,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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": [
+    1,
+    2,
+    6,
+    7,
+    8,
+    9,
+    10,
+    12,
+    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": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51865
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a596a52d36424c6e42fa49368ee2b1f7917115c6e99880ea9c28f1cc75c705
+size 151253984