---
language:
- ga
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- ymoslem/IWSLT2023-GA-EN
- ymoslem/FLEURS-GA-EN
- ymoslem/BitesizeIrish-GA-EN
- ymoslem/SpokenWords-GA-EN-MTed
- ymoslem/Tatoeba-Speech-Irish
- ymoslem/Wikimedia-Speech-Irish
- ymoslem/Tatoeba-Speech-Irish-Noise-002
- ymoslem/Wikimedia-Speech-Irish-Noise-002
model-index:
- name: Whisper Small GA-EN Speech Translation
  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. -->

# Whisper Small GA-EN Speech Translation

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia dataset.

## 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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 3000
- mixed_precision_training: Native AMP

### Training results

| **Step** | **Training Loss** | **Validation Loss** |  **Bleu** |  **Chrf** |    **Wer** |
|---------:|------------------:|--------------------:|----------:|----------:|-----------:|
|      100 |          2.351300 |            1.908078 |  6.230000 | 21.980000 | 117.424584 |
|      200 |          1.831200 |            1.567262 | 10.800000 | 30.010000 | 109.770374 |
|      300 |          1.494100 |            1.421244 | 13.550000 | 33.480000 | 120.306168 |
|      400 |          1.309900 |            1.326882 | 19.540000 | 41.060000 |  77.217470 |
|      500 |          1.069600 |            1.285087 | 19.100000 | 40.230000 |  95.767672 |
|      600 |          0.889600 |            1.255216 | 16.450000 | 38.590000 | 110.445745 |
|      700 |          0.783700 |            1.204875 | 30.430000 | 47.940000 |  63.574966 |
|      800 |          0.653300 |            1.213243 | 24.280000 | 43.240000 |  72.219721 |
|      900 |          0.585300 |            1.246309 | 29.130000 | 44.890000 |  64.295362 |
|     1000 |          0.471100 |            1.236493 | 26.550000 | 45.000000 |  70.688879 |
|     1100 |          0.228500 |            1.271864 | 26.430000 | 45.950000 |  73.525439 |
|     1200 |          0.213200 |            1.297864 | 28.940000 | 45.720000 |  65.736155 |
|     1300 |          0.184800 |            1.262461 | 27.330000 | 46.820000 |  72.264746 |
|     1400 |          0.195100 |            1.283275 | 29.740000 | 46.850000 |  64.745610 |
|     1500 |          0.172600 |            1.252396 | 29.330000 | 46.390000 |  64.655561 |
|     1600 |          0.164400 |            1.295237 | 25.880000 | 45.290000 |  74.110761 |
|     1700 |          0.144700 |            1.291115 | 24.490000 | 44.950000 |  71.994597 |
|     1800 |          0.148200 |            1.260603 | 29.300000 | 46.220000 |  63.935164 |
|     1900 |          0.115800 |            1.292712 | 29.480000 | 46.770000 |  63.980189 |
|     2000 |          0.105900 |            1.293839 | 29.150000 | 47.870000 |  67.086898 |
|     2100 |          0.086100 |            1.295070 | 28.820000 | 47.200000 |  64.700585 |
|     2200 |          0.035700 |            1.303162 | 30.170000 | 47.570000 |  64.745610 |
|     2300 |          0.032700 |            1.324677 | 27.020000 | 45.370000 |  73.075191 |
|     2400 |          0.031700 |            1.286437 | 30.480000 | 48.450000 |  63.619991 |
|     2500 |          0.031200 |            1.305244 | 32.510000 | 49.490000 |  61.278703 |
|     2600 |          0.027300 |            1.306147 | 31.860000 | 49.900000 |  63.124719 |
|     2700 |          0.027000 |            1.321022 | 32.000000 | 49.300000 |  63.124719 |
|     2800 |          0.023100 |            1.305768 | 32.190000 | 49.760000 |  61.413778 |
|     2900 |          0.020800 |            1.319407 | 32.070000 | 48.470000 |  62.179199 |
|     3000 |          0.022800 |            1.318355 | 32.150000 | 48.490000 |  61.638901 |

### Framework versions

- Transformers 4.41.2
- Pytorch 2.2.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1