Model save

README.md

@@ -6,20 +6,20 @@ tags:
 metrics:
 - wer
 model-index:
-- name: augmented_us_dataset_client4
+- name: augmented_indians_dataset_client2
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# augmented_us_dataset_client4
+# augmented_indians_dataset_client2
 
 This model is a fine-tuned version of [zainulhakim/241103_wav2vec2_Augmented_Dataset](https://huggingface.co/zainulhakim/241103_wav2vec2_Augmented_Dataset) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7301
-- Wer: 0.6762
-- Cer: 0.2881
+- Loss: 0.7949
+- Wer: 0.5314
+- Cer: 0.2484
 
 ## Model description
 
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| No log        | 1.0   | 156  | 1.4351          | 0.7952 | 0.5964 |
-| No log        | 2.0   | 312  | 0.8875          | 0.7381 | 0.3567 |
-| No log        | 3.0   | 468  | 0.7301          | 0.6762 | 0.2881 |
+| No log        | 1.0   | 156  | 1.6021          | 0.7371 | 0.5976 |
+| No log        | 2.0   | 312  | 1.0143          | 0.6057 | 0.3627 |
+| No log        | 3.0   | 468  | 0.7949          | 0.5314 | 0.2484 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9da9ff3a9edbb8d610f955f87a04b71d99f7a773a0479fb891b3738f055798
+oid sha256:53925793be2520f0824a42e16eb0bbce2481f29c1baa2f26122933903873bf91
 size 377611120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57466f6f1e247528f364f8a579b8fb2b6181cbefbb39e85af785253bfd13406a
+oid sha256:a849a709f580ec193cc5519f5b8e97a087547a79fb79c9f971f07f592b6d254a
 size 5176