End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: openai/whisper-large-v3-turbo
+base_model: ayameRushia/whisper-v3-turbo-id
 tags:
 - generated_from_trainer
 datasets:
@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 9.140284096184198
+      value: 9.17372101582628
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,39 +31,44 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-v3-turbo-id
 
-This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the common_voice_17_0 dataset.
+This model is a fine-tuned version of [ayameRushia/whisper-v3-turbo-id](https://huggingface.co/ayameRushia/whisper-v3-turbo-id) on the common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1662
-- Wer: 9.1403
+- Loss: 0.1760
+- Wer: 9.1737
 
 ## Model description
 
-Checkpoint training
-Might get better result after several iteration
+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: 2e-05
+- learning_rate: 1.5e-05
 - train_batch_size: 16
-- eval_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 300
-- training_steps: 2000
+- lr_scheduler_type: cosine
+- training_steps: 3000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.2736        | 0.9615 | 500  | 0.2721          | 18.6659 |
-| 0.1345        | 1.9231 | 1000 | 0.2059          | 13.0164 |
-| 0.0401        | 2.8846 | 1500 | 0.1831          | 10.4726 |
-| 0.0074        | 3.8462 | 2000 | 0.1662          | 9.1403  |
+| 0.0706        | 1.9231 | 1000 | 0.2361          | 18.0484 |
+| 0.0099        | 3.8462 | 2000 | 0.1875          | 10.3607 |
+| 0.001         | 5.7692 | 3000 | 0.1760          | 9.1737  |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-large-v3-turbo",
+  "_name_or_path": "ayameRushia/whisper-v3-turbo-id",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da276e5ac2873fcacbabbbe3f73f5328a0ecebd844aa1c9111ed9709b0d991a8
+oid sha256:dc24104d9cbf75bdc9090f08aa02557d3a202aff0aa01f6a84215c66dfa98f8d
 size 3235581408

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9546649d2bbb5c788bfb98a5fad975a736f9d698ff5ed632b86ba5fa4afef3
+oid sha256:0573e258105cd9aed5a089e767c3d142d1be632074cca38f6fae7e25b3c137bc
 size 5368