End of training

README.md

@@ -1,24 +1,24 @@
 ---
-base_model: facebook/wav2vec2-base
 license: apache-2.0
-metrics:
-- wer
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
-- name: 240615-wav2vec2-ASR-Chinese
+- name: 240615-wav2vec2-ASR-Indians
   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. -->
 
-# 240615-wav2vec2-ASR-Chinese
+# 240615-wav2vec2-ASR-Indians
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7811
-- Wer: 0.2254
+- Loss: 1.8686
+- Wer: 0.2850
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 6.25  | 100  | 0.7811          | 0.2254 |
-| No log        | 12.5  | 200  | 1.3569          | 0.2448 |
-| No log        | 18.75 | 300  | 0.9215          | 0.2609 |
-| No log        | 25.0  | 400  | 0.7503          | 0.3108 |
+| No log        | 6.25  | 100  | 1.8686          | 0.2850 |
+| No log        | 12.5  | 200  | 2.1553          | 0.3285 |
+| No log        | 18.75 | 300  | 1.8499          | 0.3172 |
+| No log        | 25.0  | 400  | 2.0953          | 0.3269 |
 
 
 ### Framework versions