metadata

language:
  - hi
license: apache-2.0
library_name: peft
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
base_model: openai/whisper-large-v3
model-index:
  - name: Abhinav28/large-v3-hi-common-voice-11-full
    results: []

Abhinav28/large-v3-hi-common-voice-11-full

This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.1558

Model description

Trained without fp16=True

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.1629	1.0	818	0.1558

Framework versions

PEFT 0.7.2.dev0
Transformers 4.36.2
Pytorch 2.0.0
Datasets 2.16.2.dev0
Tokenizers 0.15.0