---
language:
- en
tags:
- automatic-speech-recognition
- ahazeemi/librispeech10h
- generated_from_trainer
datasets:
- ahazeemi/librispeech10h
metrics:
- wer
pipeline_tag: automatic-speech-recognition
base_model: microsoft/wavlm-large
model-index:
- name: wavlm-libri-clean-100h-large
  results: []
---

<!-- 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. -->

# wavlm-libri-clean-100h-large

This model is a fine-tuned version of [microsoft/wavlm-large](https://huggingface.co/microsoft/wavlm-large) on the AHAZEEMI/LIBRISPEECH10H - CLEAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0893
- Wer: 0.0655

## 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: 0.0003
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0144        | 0.42  | 300  | 0.0947          | 0.0749 |
| 0.1408        | 0.84  | 600  | 0.1347          | 0.1363 |
| 0.0396        | 1.26  | 900  | 0.1090          | 0.0935 |
| 0.0353        | 1.68  | 1200 | 0.1032          | 0.0832 |
| 0.051         | 2.1   | 1500 | 0.0969          | 0.0774 |
| 0.0254        | 2.52  | 1800 | 0.0930          | 0.0715 |
| 0.0579        | 2.94  | 2100 | 0.0894          | 0.0660 |


### Framework versions

- Transformers 4.26.1
- Pytorch 2.0.0+cpu
- Datasets 2.9.0
- Tokenizers 0.13.2