README.md

metadata

language:
  - tw
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_17_0
  - mms
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: wav2vec2-twi-adapter
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: MOZILLA-FOUNDATION/COMMON_VOICE_17_0 - TW
          type: common_voice_17_0
          config: tw
          split: None
          args: 'Config: tw, Training split: train, Eval split: validation+test'
        metrics:
          - name: Wer
            type: wer
            value: 1

wav2vec2-twi-adapter

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_17_0 - TW dataset. It achieves the following results on the evaluation set:

• Loss: 2.4092
• Wer: 1.0
• Cer: 1.0

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 30.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
No log	11.1111	50	5.8930	1.0	1.0
No log	22.2222	100	2.4281	1.0	1.0

Framework versions

• Transformers 4.41.1
• Pytorch 2.0.0
• Datasets 2.19.1
• Tokenizers 0.19.1