aimonbc24 commited on
Commit
ea3a213
·
verified ·
1 Parent(s): 7a31231

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -7
README.md CHANGED
@@ -1,9 +1,15 @@
1
- This repository hosts a finetune of openai/whisper-large-v2 on Jacob's Voice data from the Secret-Sleepover-Society.
2
 
3
- The checkpoints are as follows, named with respect to total number of training steps with batch size of 2.
4
 
5
- checkpoint-6717: 1 epoch of tuning \
6
- checkpoint-10075: 1.5 epochs of tuning \
7
- checkpoint-13433: 2 epochs of tuning \
8
- checkpoint-16791: 2.5 epochs of tuning \
9
- checkpoint-20149: 3 epochs of tuning
 
 
 
 
 
 
 
1
+ # Whisper-Large-V2 Fine-Tuned on Jacob's Voice Data
2
 
3
+ This repository contains fine-tuned versions of the `openai/whisper-large-v2` model, adapted specifically for Jacob's voice data from the Secret-Sleepover-Society. The fine-tuning process involved training the model on a dataset featuring Jacob's voice, enhancing its ability to accurately transcribe his speech.
4
 
5
+ ## Model Checkpoints
6
+
7
+ The following checkpoints are provided, each representing different stages of the fine-tuning process. The checkpoints are named based on the total number of training steps, with a batch size of 2:
8
+
9
+ - **checkpoint-6717**: After 1 epoch of fine-tuning
10
+ - **checkpoint-10075**: After 1.5 epochs of fine-tuning
11
+ - **checkpoint-13433**: After 2 epochs of fine-tuning
12
+ - **checkpoint-16791**: After 2.5 epochs of fine-tuning
13
+ - **checkpoint-20149**: After 3 epochs of fine-tuning
14
+
15
+ Each checkpoint reflects the model's state at the corresponding step, allowing users to choose the version that best suits their needs.