Malwhisper-v1-medium

This model is a fine-tuned version of openai/whisper-medium fine-tuned on IMASc dataset.

About Dataset

IMaSC is a Malayalam text and speech corpus made available by ICFOSS for the purpose of developing speech technology for Malayalam, particularly text-to-speech. The corpus contains 34,473 text-audio pairs of Malayalam sentences spoken by 8 speakers, totalling in approximately 50 hours of audio.

Training

Script Used for training

Training run

Experiment Tracking with Weights and Biases

• GPUs used: A100 - 80 GB

• Training Time: 16 hours

• This project was build with A100 80GB GPU provided by E2E Cloud during their open hack day

Evaluation

The fine-tuned model on evaluating in the following dataset:

In Mozilla CommonVoice 11.0 dataset (Malayalam subset):

WER - 61.84

CER - 15.41

In SMC Malayalam Speech Corpus dataset:

WER - 70.49

CER - 17.0