End of training

README.md

@@ -3,40 +3,40 @@ library_name: transformers
 language:
 - ur
 license: apache-2.0
-base_model: GogetaBlueMUI/whisper-medium-ur
+base_model: openai/whisper-medium
 tags:
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_17_0
+- fsicoli/common_voice_19_0
 metrics:
 - wer
 model-index:
-- name: Whisper Medium Ur - Muhammad Abdullah
+- name: Whisper Medium Ur - Your Name
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice 17.0
-      type: mozilla-foundation/common_voice_17_0
+      name: Common Voice 19.0
+      type: fsicoli/common_voice_19_0
       config: ur
       split: test
       args: 'config: ur, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 28.35960496272455
+      value: 27.720097349677363
 ---
 
 <!-- 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 Ur - Muhammad Abdullah
+# Whisper Medium Ur - Your Name
 
-This model is a fine-tuned version of [GogetaBlueMUI/whisper-medium-ur](https://huggingface.co/GogetaBlueMUI/whisper-medium-ur) on the Common Voice 17.0 dataset.
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 19.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4708
-- Wer: 28.3596
+- Loss: 0.3564
+- Wer: 27.7201
 
 ## Model description
 
@@ -55,29 +55,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 7e-06
-- train_batch_size: 32
-- eval_batch_size: 16
+- learning_rate: 3e-06
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- 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_steps: 90
-- training_steps: 800
+- lr_scheduler_warmup_steps: 150
+- training_steps: 1500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.1373        | 0.5952 | 100  | 0.4251          | 27.3170 |
-| 0.081         | 1.1905 | 200  | 0.4459          | 30.8355 |
-| 0.0867        | 1.7857 | 300  | 0.4392          | 29.1326 |
-| 0.0352        | 2.3810 | 400  | 0.4708          | 28.3596 |
+| 0.3965        | 0.6557 | 500  | 0.3952          | 30.0288 |
+| 0.3086        | 1.3108 | 1000 | 0.3665          | 27.9635 |
+| 0.2877        | 1.9666 | 1500 | 0.3564          | 27.7201 |
 
 
 ### Framework versions
 
-- Transformers 4.48.2
-- Pytorch 2.3.0+cu121
-- Datasets 3.2.0
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.4.1
 - Tokenizers 0.21.0

generation_config.json

@@ -32,16 +32,6 @@
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      null
-    ],
-    [
-      2,
-      50359
-    ]
-  ],
   "is_multilingual": true,
   "lang_to_id": {
     "<|af|>": 50327,
@@ -246,5 +236,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.48.2"
+  "transformers_version": "4.49.0"
 }