README.md

metadata

language:
  - ur
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_7_0
  - generated_from_trainer
  - sv
  - robust-speech-event
  - model_for_talk
datasets:
  - common_voice
model-index:
  - name: ''
    results: []

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UR dataset. It achieves the following results on the evaluation set:

• Loss: 1.5614
• Wer: 0.6765

Model description

More information needed

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.9115	20.83	500	1.5400	0.7280
0.1155	41.67	1000	1.5614	0.6765

Framework versions

• Transformers 4.16.0.dev0
• Pytorch 1.10.1+cu102
• Datasets 1.17.1.dev0
• Tokenizers 0.11.0

Evaluation Commands

1. To evaluate on mozilla-foundation/common_voice_7_0 with split test

python eval.py --model_id Maniac/wav2vec2-xls-r-urdu --dataset mozilla-foundation/common_voice_7_0 --config ur --split test

2. To evaluate on speech-recognition-community-v2/dev_data

python eval.py --model_id Maniac/wav2vec2-xls-r-urdu --dataset speech-recognition-community-v2/dev_data --config ur --split validation --chunk_length_s 5.0 --stride_length_s 1.0