whisper-large-shona / README.md
steja's picture
shona whisper large ft
81aa243
---
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper_large_Shona
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: google/fleurs sn_zw
type: google/fleurs
config: sn_zw
split: test
metrics:
- name: Wer
type: wer
value: 37.5
---
<!-- 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_large_Shona
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the google/fleurs sn_zw dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9189
- Wer: 37.5
## 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0005 | 41.64 | 500 | 0.8784 | 37.525 |
| 0.0003 | 83.32 | 1000 | 0.9189 | 37.5 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2