---
language: 
- sv-SE

license: apache-2.0
tags:
- automatic-speech-recognition
- robust-speech-event
datasets:
- mozilla-foundation/common_voice_8_0
metrics:
- wer
- cer
model-index:
- name: wav2vec2-large-xls-r-1b-Swedish
  results:
  - task: 
      type: automatic-speech-recognition  # Required. Example: automatic-speech-recognition
      name: Speech Recognition  # Optional. Example: Speech Recognition
    dataset:
      type: mozilla-foundation/common_voice_8_0  # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
      name: Common Voice sv-SE # Required. Example: Common Voice zh-CN
      args: sv-SE       # Optional. Example: zh-CN
    metrics:
      - type: wer    # Required. Example: wer
        value: 18.03  # Required. Example: 20.90
        name: Test WER Without LM   # Optional. Example: Test WER
        args: 
        - learning_rate: 7.5e-05
        - train_batch_size: 32
        - eval_batch_size: 8
        - seed: 42
        - gradient_accumulation_steps: 4
        - total_train_batch_size: 128
        - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
        - lr_scheduler_type: linear
        - lr_scheduler_warmup_steps: 1000
        - num_epochs: 50
        - mixed_precision_training: Native AMP    # Optional. Example for BLEU: max_order
      - type: cer    # Required. Example: wer
        value: 5.69  # Required. Example: 20.90
        name: Test CER  Without LM   # Optional. Example: Test WER
        args: 
        - learning_rate: 7.5e-05
        - train_batch_size: 32
        - eval_batch_size: 8
        - seed: 42
        - gradient_accumulation_steps: 4
        - total_train_batch_size: 128
        - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
        - lr_scheduler_type: linear
        - lr_scheduler_warmup_steps: 1000
        - num_epochs: 50
        - mixed_precision_training: Native AMP
---

<!-- 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. -->

# wav2vec2-large-xls-r-1b-Swedish

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice dataset.
It achieves the following results on the evaluation set:

**Without LM**
- Loss: 0.3370
- Wer: 0.1803
- Cer: 0.0569

**With LM**



## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 7.5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 3.1423        | 5.49  | 500  | 0.5523          | 0.4414 | 0.1313 |
| 0.8615        | 10.98 | 1000 | 0.3877          | 0.2946 | 0.0942 |
| 0.4848        | 16.48 | 1500 | 0.3580          | 0.2539 | 0.0798 |
| 0.3538        | 21.97 | 2000 | 0.3391          | 0.2254 | 0.0709 |
| 0.2879        | 27.47 | 2500 | 0.3392          | 0.2151 | 0.0680 |
| 0.2466        | 32.96 | 3000 | 0.3687          | 0.2131 | 0.0680 |
| 0.2146        | 38.46 | 3500 | 0.3551          | 0.1951 | 0.0618 |
| 0.1916        | 43.95 | 4000 | 0.3601          | 0.1867 | 0.0590 |
| 0.175         | 49.45 | 4500 | 0.3370          | 0.1803 | 0.0569 |


### Framework versions

- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2.dev0
- Tokenizers 0.11.0