This model is a fine-tuned version of
openai/whisper-small on the
Common Voice 17.0 and
surafelabebe/fleurs_am (a subset of
google/fleurs) datasets.
It achieves the following results on the evaluation set:
The model was trained for 10 hours on T4 GPU. Training results indicate potential overfitting. Future improvements will focus on mitigating this by incorporating a larger dataset, extended training epochs, and dropout regularization.
1from transformers import pipeline
2
3pipe = pipeline(model="surafelabebe/whisper-small-am")
4
5text = pipe("sample.wav")["text"] # change to "your audio file name"
6
7print(text)
The fine-tuning process followed a similar procedure to that described in
this blog post.
