whisper-medium-bg / README.md
shripadbhat's picture
Update README.md
7bf3b4d
---
language:
- bg
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
- hf-asr-leaderboard
datasets:
- mozilla-foundation/common_voice_11_0
model-index:
- name: Whisper Medium Bulgarian
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: bg
split: test
args: bg
metrics:
- name: Wer
type: wer
value: 18.7606
---
<!-- 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 Medium Bulgarian
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.3423
- eval_wer: 18.7606
- eval_runtime: 1297.1096
- eval_samples_per_second: 1.402
- eval_steps_per_second: 0.044
- epoch: 5.48
- step: 400
## 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: 16
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- 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: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2