metadata

language:
  - hi
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_15_0
  - mms
  - generated_from_trainer
datasets:
  - common_voice_15_0
metrics:
  - wer
model-index:
  - name: RohitDataScienceSpeechAnalyticsOutput
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI
          type: common_voice_15_0
          config: hi
          split: validation
          args: 'Config: hi, Training split: train, Eval split: validation'
        metrics:
          - name: Wer
            type: wer
            value: 1.0016248153618907

RohitDataScienceSpeechAnalyticsOutput

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI dataset. It achieves the following results on the evaluation set:

Loss: 20.2731
Wer: 1.0016

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
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 1.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.6897	100	21.9156	1.0006

Framework versions

Transformers 4.42.0.dev0
Pytorch 2.3.0
Datasets 2.19.1
Tokenizers 0.19.1