End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 46.700316900258095
+      value: 45.28733379071515
 ---
 
 <!-- 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-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6650
-- Wer: 46.7003
+- Loss: 0.6882
+- Wer: 45.2873
 
 ## Model description
 
@@ -54,21 +54,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 16
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
 - 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: 500
-- training_steps: 2100
+- lr_scheduler_warmup_steps: 2
+- training_steps: 1100
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.7437        | 0.6439 | 1000 | 1.0007          | 63.6414 |
-| 0.2322        | 1.2878 | 2000 | 0.6650          | 46.7003 |
+| 0.1129        | 1.2870 | 1000 | 0.6882          | 45.2873 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-tiny",
+  "_name_or_path": "ambind/whisper-tiny-pl",
   "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 sha256:87ea774a2ffaca4d5fc0410a3ffd3e51b975f055dd6462d60ea938578418c1a6
+oid sha256:47e60e0d77b9858650360c146570bfa26f16db24f933d1af5e743165d485aab6
 size 151061672

runs/Nov05_13-06-13_38c9da7b177a/events.out.tfevents.1730811993.38c9da7b177a.1852.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8f855bdaa51491bbf9d7373097e8f7fafdad1323a1fd2ac33b75a0acea0827
+size 15829

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7210a3b8ad424dd8cd5026ec6607604f945d21e0a8e94d3981a95b4e636a85
+oid sha256:80007c752f5787eb62dcd34e8bc537810317aa38d8114c56dd937a1bb99e8e1a
 size 5368