End of training

README.md

@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 99.54022988505747
+      value: 94.94252873563218
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ 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: 1.0757
-- Wer: 99.5402
+- Loss: 1.1350
+- Wer: 94.9425
 
 ## Model description
 
@@ -62,14 +62,15 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.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: 10
-- training_steps: 5000
+- training_steps: 10000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer     |
-|:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.0001        | 46.2963 | 5000 | 1.0757          | 99.5402 |
+| Training Loss | Epoch   | Step  | Validation Loss | Wer     |
+|:-------------:|:-------:|:-----:|:---------------:|:-------:|
+| 0.0001        | 46.2963 | 5000  | 1.0784          | 96.5517 |
+| 0.0           | 92.5926 | 10000 | 1.1350          | 94.9425 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2039fc95c22523b55c17dc751a3ffe17c2508420221bd45ab56fe69407d36f09
+oid sha256:6d231cb6652e30460b27400b8c61c7bb2ff5ed9aee28860f95685e6d8eb64cf5
 size 151061672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00086c7fe03aa82f799e71c25ff400a586854078eb20e660a7b8fb76787dbebf
+oid sha256:3d346f5c46e4963df866c322bae80a16b6d6d30d0cf73fe3d247bf92eb41968c
 size 5496