---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: fine-tune-wav2vec2-large-xls-r-1b-sw
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: common_voice_11_0
      type: common_voice_11_0
      config: sw
      split: test[:1%]
      args: sw
    metrics:
    - name: Wer
      type: wer
      value: 0.5834348355663824
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# fine-tune-wav2vec2-large-xls-r-300m-sw

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_11_0 swahili dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2834
- Wer: 0.5834

## Model description

This model is fine-tuned for general swahili speech recognition tasks. You can watch our hour long [webinar](https://drive.google.com/file/d/1OkLx3d9xivdyxH8yYsZtwObhEX5Ptn5y/view?usp=drive_link) and see the [slides](https://docs.google.com/presentation/d/1sExJLwZLMNMKGnpuxy-ttF5KqDXJyKK2jNNTUabo5_Q/edit?usp=sharing) on this work.

## Intended uses & limitations

The intention is to transcribe general swahili speeches. With further development, we'll fine-tune the model for domain-specific (we are focused on hospital tasks) swahili conversations.

## Training and evaluation data

To appreciate the transformation we did on the data, you can read our [blog on data preparation](https://medium.com/@gitau_am/from-raw-data-to-accurate-speech-recognition-asr-my-journey-of-data-preparation-df3a1b0dee3a).

## Training procedure
We also [documented](https://medium.com/@gitau_am/exploring-asr-model-development-fine-tuning-xls-r-wav2vec2-model-with-swahili-data-b95134d116b8) some lessons from the fine-tuning exercise.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 9
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log        | 1.72  | 200  | 3.0092          | 1.0    |
| 4.1305        | 3.43  | 400  | 2.9159          | 1.0    |
| 4.1305        | 5.15  | 600  | 1.4301          | 0.7040 |
| 0.9217        | 6.87  | 800  | 1.3143          | 0.6529 |
| 0.9217        | 8.58  | 1000 | 1.2834          | 0.5834 |


### Framework versions

- Transformers 4.27.0
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2