End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 113.38155515370704
+      value: 8.930987821380242
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6453
-- Wer: 113.3816
+- Loss: 0.1879
+- Wer: 8.9310
 
 ## Model description
 
@@ -54,11 +54,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
@@ -67,12 +67,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer      |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.1814        | 1.5873 | 50   | 0.5060          | 113.3816 |
-| 0.0763        | 3.1746 | 100  | 0.5619          | 113.5624 |
-| 0.0147        | 4.7619 | 150  | 0.6322          | 113.3816 |
-| 0.0015        | 6.3492 | 200  | 0.6453          | 113.3816 |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.1815        | 0.5   | 50   | 0.2587          | 12.7876 |
+| 0.2653        | 1.0   | 100  | 0.1937          | 10.0474 |
+| 0.074         | 1.5   | 150  | 0.2002          | 10.7578 |
+| 0.0625        | 2.0   | 200  | 0.1879          | 8.9310  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e8c35137b9fe5e3ee62a59d79e3724d51dfb8c20e6ff02534b1f2909547aef
+oid sha256:de2ac8e42503f5655540047ec6b1bd637e2d5dfd35862c0e3429a579c5d44fb2
 size 966995080

runs/Sep06_14-22-46_Mohit/events.out.tfevents.1725612813.Mohit.16292.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c31fa24c6250a88ed502a2042d2d4a0f7c4732815ffa7c50022f35d5933945
+size 6888

runs/Sep06_15-12-10_Mohit/events.out.tfevents.1725615733.Mohit.17428.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0b4a1c2779f1c5160d396863f9c3d19024588938a59b9df203a9e37b58299b
+size 6681

runs/Sep06_15-23-04_Mohit/events.out.tfevents.1725616387.Mohit.17428.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e764525bf06074c6b842871ca0963c0fac2e963f6e9794f59d96c0e7a2a22ff
+size 6681

runs/Sep06_15-24-44_Mohit/events.out.tfevents.1725616488.Mohit.18756.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e4abd6dd13db08a0b0b9f1875b2956ecdea6db6ae03456da476d1438bc7d34
+size 12467

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1672227cd7fc9f1172156fd8f2fb0e1ee3815fce711ab64abc92a36358d89e2
+oid sha256:98cf4f8bdd0718cf0366f5157c44be16330788cb98951649be0b0aebb4c19d2f
 size 5304