Upload TFWhisperForConditionalGeneration

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: whisper_werbest
+  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_werbest
+
+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: 0.3071
+- Train Accuracy: 0.0324
+- Train Wermet: 1.7931
+- Validation Loss: 0.5766
+- Validation Accuracy: 0.0312
+- Validation Wermet: 1.5663
+- Epoch: 14
+
+## 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 |
+|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
+| 5.0795     | 0.0116         | 43.8776      | 4.4395          | 0.0122              | 35.4119           | 0     |
+| 4.3059     | 0.0131         | 29.7976      | 4.0311          | 0.0143              | 26.0070           | 1     |
+| 3.8871     | 0.0148         | 19.3999      | 3.6500          | 0.0158              | 19.2186           | 2     |
+| 3.0943     | 0.0184         | 18.3704      | 2.3327          | 0.0226              | 22.5034           | 3     |
+| 1.8954     | 0.0240         | 16.2471      | 1.4889          | 0.0266              | 14.2782           | 4     |
+| 1.2781     | 0.0269         | 8.4169       | 1.1273          | 0.0283              | 7.4581            | 5     |
+| 0.9797     | 0.0283         | 4.8739       | 0.9481          | 0.0292              | 3.9451            | 6     |
+| 0.8006     | 0.0293         | 2.7433       | 0.8371          | 0.0297              | 2.3065            | 7     |
+| 0.6764     | 0.0299         | 2.1646       | 0.7554          | 0.0301              | 1.3005            | 8     |
+| 0.5820     | 0.0305         | 1.5323       | 0.6980          | 0.0305              | 1.1238            | 9     |
+| 0.5078     | 0.0310         | 1.4328       | 0.6617          | 0.0306              | 1.2793            | 10    |
+| 0.4455     | 0.0314         | 1.4891       | 0.6252          | 0.0309              | 1.6833            | 11    |
+| 0.3927     | 0.0317         | 1.6700       | 0.6123          | 0.0310              | 2.1091            | 12    |
+| 0.3473     | 0.0321         | 1.6245       | 0.5851          | 0.0311              | 1.4109            | 13    |
+| 0.3071     | 0.0324         | 1.7931       | 0.5766          | 0.0312              | 1.5663            | 14    |
+
+
+### Framework versions
+
+- Transformers 4.25.0.dev0
+- TensorFlow 2.9.2
+- Datasets 2.6.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,92 @@
+{
+  "_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,
+      50289
+    ],
+    [
+      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": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    10968,
+    10969,
+    10970,
+    10971,
+    10972,
+    10973,
+    10974,
+    10975,
+    10976,
+    10977,
+    10978,
+    10979,
+    10980,
+    10981,
+    10982,
+    10983,
+    10984,
+    10985,
+    10986,
+    10987,
+    10988,
+    10989,
+    10990,
+    10991,
+    10992,
+    10993,
+    10994,
+    10995,
+    10996,
+    10997,
+    50256
+  ],
+  "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:f15a211305c75fd1a6445b17f681006fbdad2ba01f294f7d4f34ba52f248fc7b
+size 151253984