asr-wav2vec2-1b-asm
This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2854
- Wer: 0.8947
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: 16
- 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: 200
- num_epochs: 14
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.6749 | 2.7027 | 200 | 0.3014 | 0.9074 |
| 0.3157 | 5.4054 | 400 | 0.2934 | 0.9038 |
| 0.2644 | 8.1081 | 600 | 0.2894 | 0.9147 |
| 0.2264 | 10.8108 | 800 | 0.2865 | 0.9020 |
| 0.1972 | 13.5135 | 1000 | 0.2854 | 0.8947 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for madhabpaul/asr-wav2vec2-1b-asm
Base model
facebook/mms-1b-all