Model save

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: openai/whisper-medium.en
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: whisper-medium.en-cit-do015-wd0-lr1e-06-SF-400
+  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. -->
+
+# whisper-medium.en-cit-do015-wd0-lr1e-06-SF-400
+
+This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7217
+- Wer Ortho: 29.6283
+- Wer: 19.5551
+
+## 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: 1e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 200
+- training_steps: 500
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
+| 1.6015        | 4.0   | 100  | 1.1045          | 41.2901   | 30.3911 |
+| 0.8237        | 8.0   | 200  | 0.7959          | 31.3776   | 20.4880 |
+| 0.5824        | 12.0  | 300  | 0.7417          | 29.7741   | 19.3757 |
+| 0.4724        | 16.0  | 400  | 0.7256          | 29.5554   | 19.4474 |
+| 0.4232        | 20.0  | 500  | 0.7217          | 29.6283   | 19.5551 |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 1.13.1+cu117
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -2,7 +2,7 @@
   "_name_or_path": "openai/whisper-medium.en",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
-  "apply_spec_augment": true,
+  "apply_spec_augment": false,
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
@@ -19,7 +19,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 24,
   "decoder_start_token_id": 50257,
-  "dropout": 0.15,
+  "dropout": 0,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,

generation_config.json

@@ -0,0 +1,188 @@
+{
+  "alignment_heads": [
+    [
+      11,
+      4
+    ],
+    [
+      14,
+      1
+    ],
+    [
+      14,
+      12
+    ],
+    [
+      14,
+      14
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      16,
+      0
+    ],
+    [
+      16,
+      4
+    ],
+    [
+      16,
+      9
+    ],
+    [
+      17,
+      12
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      18,
+      7
+    ],
+    [
+      18,
+      10
+    ],
+    [
+      18,
+      15
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      20,
+      3
+    ],
+    [
+      20,
+      9
+    ],
+    [
+      20,
+      14
+    ],
+    [
+      21,
+      12
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50257,
+  "eos_token_id": 50256,
+  "is_multilingual": false,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50362,
+  "pad_token_id": 50256,
+  "prev_sot_token_id": 50360,
+  "return_timestamps": false,
+  "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,
+    357,
+    366,
+    438,
+    532,
+    685,
+    705,
+    796,
+    930,
+    1058,
+    1220,
+    1267,
+    1279,
+    1303,
+    1343,
+    1377,
+    1391,
+    1635,
+    1782,
+    1875,
+    2162,
+    2361,
+    2488,
+    3467,
+    4008,
+    4211,
+    4600,
+    4808,
+    5299,
+    5855,
+    6329,
+    7203,
+    9609,
+    9959,
+    10563,
+    10786,
+    11420,
+    11709,
+    11907,
+    13163,
+    13697,
+    13700,
+    14808,
+    15306,
+    16410,
+    16791,
+    17992,
+    19203,
+    19510,
+    20724,
+    22305,
+    22935,
+    27007,
+    30109,
+    30420,
+    33409,
+    34949,
+    40283,
+    40493,
+    40549,
+    47282,
+    49146,
+    50257,
+    50357,
+    50358,
+    50359,
+    50360,
+    50361
+  ],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.44.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ab1077d35e82e1ba7a5275ed3d373f072c7e05e62a1678e96dac6f8a810546
+oid sha256:6a1dc496b29e889558d21f8ba3c4996bb24004693d95398a9d7aef05689dee9e
 size 1634043280

runs/Aug13_14-10-31_whisper-finetuning/events.out.tfevents.1723558248.whisper-finetuning

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1ccb6c218bee9762cd8298ac73d67a2e1b9cd9b9029f8c4f80570f4fab9872
-size 9628
+oid sha256:e2216e7fa08f3d09975dcccc63f628e534acf46c9766fc53c26e8ff0a5602f41
+size 9982