Upload TFWhisperForConditionalGeneration

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: whisper_havest_0025
+  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_havest_0025
+
+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: 0.0787
+- Train Accuracy: 0.0343
+- Validation Loss: 0.5796
+- Validation Accuracy: 0.0314
+- 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 |
+|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
+| 5.0949     | 0.0116         | 4.4444          | 0.0124              | 0     |
+| 4.3242     | 0.0130         | 4.0648          | 0.0140              | 1     |
+| 3.9308     | 0.0145         | 3.6837          | 0.0157              | 2     |
+| 3.5552     | 0.0159         | 3.3410          | 0.0171              | 3     |
+| 3.1591     | 0.0175         | 2.8089          | 0.0198              | 4     |
+| 2.2408     | 0.0221         | 1.7104          | 0.0255              | 5     |
+| 1.4220     | 0.0261         | 1.2181          | 0.0279              | 6     |
+| 1.0460     | 0.0280         | 0.9912          | 0.0290              | 7     |
+| 0.8363     | 0.0291         | 0.8645          | 0.0296              | 8     |
+| 0.6967     | 0.0299         | 0.7748          | 0.0301              | 9     |
+| 0.5942     | 0.0305         | 0.7201          | 0.0304              | 10    |
+| 0.5151     | 0.0309         | 0.6675          | 0.0307              | 11    |
+| 0.4496     | 0.0314         | 0.6382          | 0.0308              | 12    |
+| 0.3951     | 0.0318         | 0.6060          | 0.0310              | 13    |
+| 0.3473     | 0.0321         | 0.5945          | 0.0311              | 14    |
+| 0.3053     | 0.0324         | 0.5752          | 0.0312              | 15    |
+| 0.2684     | 0.0327         | 0.5700          | 0.0313              | 16    |
+| 0.2355     | 0.0330         | 0.5651          | 0.0313              | 17    |
+| 0.2065     | 0.0332         | 0.5619          | 0.0313              | 18    |
+| 0.1785     | 0.0334         | 0.5522          | 0.0314              | 19    |
+| 0.1535     | 0.0337         | 0.5609          | 0.0313              | 20    |
+| 0.1310     | 0.0339         | 0.5590          | 0.0314              | 21    |
+| 0.1115     | 0.0340         | 0.5695          | 0.0313              | 22    |
+| 0.0951     | 0.0342         | 0.5723          | 0.0314              | 23    |
+| 0.0787     | 0.0343         | 0.5796          | 0.0314              | 24    |
+
+
+### Framework versions
+
+- Transformers 4.25.0.dev0
+- TensorFlow 2.9.2
+- Datasets 2.6.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,199 @@
+{
+  "_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,
+    50257,
+    50258,
+    50259,
+    50260,
+    50261,
+    50262,
+    50263,
+    50264,
+    50265,
+    50266,
+    50267,
+    50268,
+    50269,
+    50270,
+    50271,
+    50272,
+    50273,
+    50274,
+    50275,
+    50276,
+    50277,
+    50278,
+    50279,
+    50280,
+    50281,
+    50282,
+    50283,
+    50284,
+    50285,
+    50286,
+    50287,
+    50288,
+    50289,
+    50290,
+    50291,
+    50292,
+    50293,
+    50294,
+    50295,
+    50296,
+    50297,
+    50298,
+    50299,
+    50300,
+    50301,
+    50302,
+    50303,
+    50304,
+    50305,
+    50306,
+    50307,
+    50308,
+    50309,
+    50310,
+    50311,
+    50312,
+    50313,
+    50314,
+    50315,
+    50316,
+    50317,
+    50318,
+    50319,
+    50320,
+    50321,
+    50322,
+    50323,
+    50324,
+    50325,
+    50326,
+    50327,
+    50328,
+    50329,
+    50330,
+    50331,
+    50332,
+    50333,
+    50334,
+    50335,
+    50336,
+    50337,
+    50338,
+    50339,
+    50340,
+    50341,
+    50342,
+    50343,
+    50344,
+    50345,
+    50346,
+    50347,
+    50348,
+    50349,
+    50350,
+    50351,
+    50352,
+    50353,
+    50354,
+    50355,
+    50356,
+    50357,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "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 sha256:3502027ca22ab03b0d00a319bcdb69aaef91ff2f5649c8b7d20903a20e89ea78
+size 151253984