YAML Metadata Error: "language[0]" with value "rm-vallader" is not valid. It must be an ISO 639-1, 639-2 or 639-3 code (two/three letters), or a special value like "code", "multilingual". If you want to use BCP-47 identifiers, you can specify them in language_bcp47.

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - RM-VALLADER dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2754
  • Wer: 0.2831

Evaluation Commands

  1. To evaluate on mozilla-foundation/common_voice_8_0 with test split

python eval.py --model_id DrishtiSharma/wav2vec2-xls-r-300m-rm-vallader-d1 --dataset mozilla-foundation/common_voice_8_0 --config rm-vallader --split test --log_outputs

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

Romansh-Vallader language not found in speech-recognition-community-v2/dev_data

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 7.5e-05
  • train_batch_size: 32
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 100.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.927 15.15 500 2.9196 1.0
1.3835 30.3 1000 0.5879 0.5866
0.7415 45.45 1500 0.3077 0.3316
0.5575 60.61 2000 0.2735 0.2954
0.4581 75.76 2500 0.2707 0.2802
0.3977 90.91 3000 0.2785 0.2809

Framework versions

  • Transformers 4.17.0.dev0
  • Pytorch 1.10.2+cu102
  • Datasets 1.18.2.dev0
  • Tokenizers 0.11.0
Downloads last month
13
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train DrishtiSharma/wav2vec2-xls-r-300m-rm-vallader-d1

Evaluation results