Model save

README.md

@@ -0,0 +1,79 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: YoussefAshmawy/Graduation_Project_Whisper_base
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: Graduation_Project_distillation_Whisper_base2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Graduation_Project_distillation_Whisper_base2
+
+This model is a fine-tuned version of [YoussefAshmawy/Graduation_Project_Whisper_base](https://huggingface.co/YoussefAshmawy/Graduation_Project_Whisper_base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1269
+- Wer: 0.4067
+
+## 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:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer    |
+|:-------------:|:-------:|:----:|:---------------:|:------:|
+| 12.6571       | 1.0     | 469  | 0.0985          | 0.5863 |
+| 3.596         | 2.0     | 938  | 0.0901          | 0.4695 |
+| 1.7624        | 3.0     | 1407 | 0.1011          | 0.4507 |
+| 1.1052        | 4.0     | 1876 | 0.1067          | 0.4320 |
+| 0.7406        | 5.0     | 2345 | 0.1194          | 0.4031 |
+| 0.4646        | 6.0     | 2814 | 0.1182          | 0.4420 |
+| 0.3698        | 7.0     | 3283 | 0.1201          | 0.4309 |
+| 0.2819        | 8.0     | 3752 | 0.1177          | 0.3808 |
+| 0.2221        | 9.0     | 4221 | 0.1144          | 0.3605 |
+| 0.1999        | 10.0    | 4690 | 0.1112          | 0.3871 |
+| 0.1506        | 11.0    | 5159 | 0.1104          | 0.3878 |
+| 0.1271        | 12.0    | 5628 | 0.1095          | 0.3966 |
+| 0.1034        | 13.0    | 6097 | 0.1102          | 0.3931 |
+| 0.0816        | 14.0    | 6566 | 0.1113          | 0.4061 |
+| 0.0647        | 14.9685 | 7020 | 0.1114          | 0.3778 |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

generation_config.json

@@ -0,0 +1,228 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "YoussefAshmawy/Graduation_Project_Whisper_base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_cross_attention": false,
+  "alignment_heads": [
+    [
+      3,
+      1
+    ],
+    [
+      4,
+      2
+    ],
+    [
+      4,
+      3
+    ],
+    [
+      4,
+      7
+    ],
+    [
+      5,
+      1
+    ],
+    [
+      5,
+      2
+    ],
+    [
+      5,
+      4
+    ],
+    [
+      5,
+      6
+    ]
+  ],
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 50257,
+  "chunk_size_feed_forward": 0,
+  "classifier_proj_size": 256,
+  "cross_attention_hidden_size": null,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 2,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 50257,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "init_std": 0.02,
+  "input_ids": [
+    [
+      1,
+      50272
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "is_decoder": false,
+  "is_encoder_decoder": true,
+  "is_multilingual": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "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_initial_timestamp_index": 50,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "no_timestamps_token_id": 50363,
+  "num_hidden_layers": 6,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "prefix": null,
+  "prev_sot_token_id": 50361,
+  "problem_type": null,
+  "pruned_heads": {},
+  "return_dict": true,
+  "return_timestamps": false,
+  "scale_embedding": false,
+  "sep_token_id": null,
+  "task_specific_params": null,
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": true,
+  "tokenizer_class": null,
+  "torchscript": false,
+  "transformers_version": "4.51.3",
+  "use_bfloat16": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5ffdae4dc3ec5d2330a531a00b56aba3e782dc7ff3adf4e6ce19d37d1448de
+oid sha256:0a68b3521e9bd50271e376efca2d88b8dac8811b5ddf1f1e34f1d40768a442e5
 size 223144592

runs/Jun17_11-33-36_835254aa27d9/events.out.tfevents.1750189031.835254aa27d9.19.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b944bfdab7ff961d27e9578c22f64735342cc7fb7d83a535aaf1d6403322e2c
+size 406