Model save

README.md

@@ -1,9 +1,11 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: pierreguillou/whisper-medium-portuguese
+license: mit
+base_model: openai/whisper-large-v3-turbo
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: whisper-finetuned
   results: []
@@ -14,7 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-finetuned
 
-This model is a fine-tuned version of [pierreguillou/whisper-medium-portuguese](https://huggingface.co/pierreguillou/whisper-medium-portuguese) on an unknown dataset.
+This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3011
+- Wer: 30.6945
 
 ## Model description
 
@@ -33,28 +38,42 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 8
+- learning_rate: 9e-06
+- train_batch_size: 4
+- eval_batch_size: 16
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 4
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 256
-- total_eval_batch_size: 32
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
 - optimizer: Use 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_ratio: 0.15
-- num_epochs: 3
+- lr_scheduler_warmup_steps: 500
+- training_steps: 6000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.3654        | 0.3680 | 500  | 0.3516          | 35.6868 |
+| 0.3355        | 0.7360 | 1000 | 0.3341          | 35.0002 |
+| 0.2826        | 1.1041 | 1500 | 0.3248          | 34.6635 |
+| 0.2763        | 1.4721 | 2000 | 0.3171          | 33.6200 |
+| 0.2715        | 1.8401 | 2500 | 0.3101          | 33.1267 |
+| 0.2203        | 2.2081 | 3000 | 0.3071          | 31.3256 |
+| 0.2202        | 2.5761 | 3500 | 0.3019          | 30.5031 |
+| 0.2169        | 2.9442 | 4000 | 0.2975          | 30.7246 |
+| 0.1765        | 3.3122 | 4500 | 0.3002          | 31.2968 |
+| 0.1768        | 3.6802 | 5000 | 0.2985          | 30.5046 |
+| 0.1594        | 4.0482 | 5500 | 0.3003          | 30.5781 |
+| 0.1603        | 4.4162 | 6000 | 0.3011          | 30.6945 |
 
 
 ### Framework versions
 
 - Transformers 4.46.0.dev0
-- Pytorch 2.2.0+cu121
+- Pytorch 2.1.0+cu118
 - Datasets 3.0.2.dev0
 - Tokenizers 0.20.0

events.out.tfevents.1728417412.9f9e9923fdea.9716.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c56b4050ef9fce8032cb00073b6246ebca28d8287da16f5d79d5de0df6430a35
-size 60399
+oid sha256:27c3d420df69bf7c4fb8989274ab42298dec885bbf07efd62a9a02d48c673d98
+size 60753

generation_config.json

@@ -1,5 +1,30 @@
 {
-  "_from_model_config": true,
+  "alignment_heads": [
+    [
+      2,
+      4
+    ],
+    [
+      2,
+      11
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      6
+    ],
+    [
+      3,
+      11
+    ],
+    [
+      3,
+      14
+    ]
+  ],
   "begin_suppress_tokens": [
     220,
     50257
@@ -7,8 +32,129 @@
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50360
+    ]
+  ],
+  "is_multilingual": true,
+  "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,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
   "max_length": 448,
+  "no_timestamps_token_id": 50364,
   "pad_token_id": 50257,
-  "transformers_version": "4.46.0.dev0",
-  "use_cache": false
+  "prev_sot_token_id": 50362,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.46.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11fa079f7d5ece9014bf0544d68a1c2c90f4b5eedc05d1711868f85ab017869
+oid sha256:d4e810beee26a08075203b9aa1a9d0efacd4dcbcf0e77687d692e84222930fc1
 size 3235581408