Upload TFWhisperForConditionalGeneration

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: openai/whisper-tiny
+tags:
+- generated_from_keras_callback
+model-index:
+- name: whisper_input_decoder_shift_r_labels_no_force__0015
+  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_input_decoder_shift_r_labels_no_force__0015
+
+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: 3.3069
+- Train Accuracy: 0.0148
+- Train Wermet: 0.6961
+- Validation Loss: 3.1102
+- Validation Accuracy: 0.0124
+- Validation Wermet: 0.7609
+- 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 |
+|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
+| 5.6348     | 0.0091         | 1.5865       | 4.2935          | 0.0093              | 0.9579            | 0     |
+| 4.9212     | 0.0099         | 0.9054       | 4.1262          | 0.0097              | 0.9390            | 1     |
+| 4.6819     | 0.0107         | 0.8319       | 3.9071          | 0.0103              | 0.8966            | 2     |
+| 4.4443     | 0.0114         | 0.8310       | 3.7367          | 0.0106              | 0.8939            | 3     |
+| 4.2479     | 0.0119         | 0.8226       | 3.6101          | 0.0109              | 0.8696            | 4     |
+| 4.0911     | 0.0124         | 0.8103       | 3.5364          | 0.0110              | 0.8946            | 5     |
+| 3.9590     | 0.0127         | 0.7913       | 3.4556          | 0.0113              | 0.8388            | 6     |
+| 3.8513     | 0.0130         | 0.7794       | 3.4106          | 0.0114              | 0.8515            | 7     |
+| 3.7607     | 0.0133         | 0.7657       | 3.3507          | 0.0115              | 0.8261            | 8     |
+| 3.6757     | 0.0136         | 0.7548       | 3.3141          | 0.0116              | 0.8400            | 9     |
+| 3.6023     | 0.0138         | 0.7454       | 3.2711          | 0.0117              | 0.8006            | 10    |
+| 3.5261     | 0.0140         | 0.7348       | 3.2391          | 0.0119              | 0.8101            | 11    |
+| 3.4534     | 0.0143         | 0.7212       | 3.2070          | 0.0120              | 0.7870            | 12    |
+| 3.3814     | 0.0146         | 0.7080       | 3.1505          | 0.0122              | 0.7826            | 13    |
+| 3.3069     | 0.0148         | 0.6961       | 3.1102          | 0.0124              | 0.7609            | 14    |
+
+
+### Framework versions
+
+- Transformers 4.34.0.dev0
+- TensorFlow 2.13.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,51 @@
+{
+  "_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": [],
+  "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": "4.34.0.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": "4.34.0.dev0"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1f8d2ac02500d53804ad788fff5cad2abafd2a4bafe44a5758961f6c3b37eb
+size 151253960