wav2vec2-xls-r-300m-swahili-cv-fleurs-alffa-word
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2057
- Wer: 0.2194
- Cer: 0.1098
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: 0.0002
- 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_ratio: 0.1
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.3702 | 1.0 | 1961 | 0.2878 | 0.3335 | 0.1367 |
| 0.2333 | 2.0 | 3922 | 0.2324 | 0.2653 | 0.1219 |
| 0.172 | 3.0 | 5883 | 0.2136 | 0.2464 | 0.1162 |
| 0.1331 | 4.0 | 7844 | 0.2043 | 0.2287 | 0.1127 |
| 0.1018 | 5.0 | 9805 | 0.2057 | 0.2194 | 0.1098 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.3.1
- Datasets 2.19.2
- Tokenizers 0.20.1
- Downloads last month
- 75
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 bookbot/wav2vec2-xls-r-300m-swahili-cv-fleurs-alffa-word-lm
Base model
facebook/wav2vec2-xls-r-300m