Model save

README.md

@@ -1,10 +1,8 @@
 ---
 license: apache-2.0
+base_model: openai/whisper-large-v2
 tags:
 - generated_from_trainer
-base_model: openai/whisper-large-v2
-metrics:
-- wer
 model-index:
 - name: BA_Model_V3
   results: []
@@ -16,10 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
 # BA_Model_V3
 
 This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6517
-- Wer: 30.2798
-- Cer: 16.8330
 
 ## Model description
 
@@ -38,34 +32,18 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 1e-06
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- lr_scheduler_type: cosine_with_restarts
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 8
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Wer     | Cer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| 0.3941        | 1.0   | 278  | 0.5114          | 33.8716 | 18.9383 |
-| 0.3497        | 2.0   | 556  | 0.5683          | 35.4898 | 19.7814 |
-| 0.2096        | 3.0   | 834  | 0.6234          | 36.9584 | 19.3400 |
-| 0.1189        | 4.0   | 1112 | 0.6315          | 33.4596 | 17.0659 |
-| 0.0715        | 5.0   | 1390 | 0.6617          | 34.9349 | 18.4059 |
-| 0.0359        | 6.0   | 1668 | 0.6752          | 33.8384 | 18.5525 |
-| 0.0141        | 7.0   | 1946 | 0.6479          | 31.8215 | 16.5859 |
-| 0.0047        | 8.0   | 2224 | 0.6384          | 31.2699 | 17.4014 |
-| 0.0013        | 9.0   | 2502 | 0.6498          | 30.2532 | 16.7700 |
-| 0.0016        | 10.0  | 2780 | 0.6517          | 30.2798 | 16.8330 |
-
-
 ### Framework versions
 
 - Transformers 4.38.2

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc21efc062cfd67bbab45c823975f1772368c63aa78fd33dba50e489894ab9c3
+oid sha256:787be19c9124e16edff2523a784c73e50669cf070f1a0fdb350971c1746ded2d
 size 4992706480

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4dd7da5de3b303468ed502b588a616a5680ffb42069bf2e4f61ac6a56fb3708
+oid sha256:7c53791d8c2915f8c4c40b337407bc6ca118ead3f6cb2a88d48cf195c2b1cd9e
 size 1180663192

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30201432c5bcf76ef2197af3070c7e4e7058f52ecf03498e6252ab59c5c6a20
-size 5048
+oid sha256:8e1640b2dce348e90b06d9d280df25b32c7c69c1cb0d6883d3a2dd66cd585fbc
+size 5112