Jacaranda-Health
/

ASR-STT

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions

Jacaranda commited on Jun 22, 2025

Commit

4fca98d

·

verified ·

1 Parent(s): ee8e977

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -161,12 +161,12 @@ The fine-tuned model demonstrates superior performance in:
 The following charts illustrate the model's training progress and performance improvements:
 ### Word Error Rate (WER) Progress
-![WER Progress](./Assets/wer.png)
 The WER chart shows the steady improvement in transcription accuracy throughout the training process. Starting from approximately 21.6% WER at step 500, the model achieves its best performance of 14.7% WER by step 8000, demonstrating consistent learning and convergence.
 ### Learning Rate Schedule
-![Learning Rate](./Assets/lr.png)
 The learning rate follows a cosine annealing schedule, starting at 1e-05 and gradually decreasing over the 8000 training steps. This schedule helps ensure stable training and prevents overfitting while allowing the model to fine-tune effectively.

 The following charts illustrate the model's training progress and performance improvements:
 ### Word Error Rate (WER) Progress
+![WER Progress](./Media/wer.png)
 The WER chart shows the steady improvement in transcription accuracy throughout the training process. Starting from approximately 21.6% WER at step 500, the model achieves its best performance of 14.7% WER by step 8000, demonstrating consistent learning and convergence.
 ### Learning Rate Schedule
+![Learning Rate](./Media/lr.png)
 The learning rate follows a cosine annealing schedule, starting at 1e-05 and gradually decreasing over the 8000 training steps. This schedule helps ensure stable training and prevents overfitting while allowing the model to fine-tune effectively.