---
language:
- ro
license: apache-2.0
tags:
- whisper-event
datasets:
- mozilla-foundation/common_voice_11_0
- gigant/romanian_speech_synthesis_0_8_1
metrics:
- wer
pinned: true
base_model: openai/whisper-medium
model-index:
- name: Whisper Medium Romanian
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: mozilla-foundation/common_voice_11_0 ro
      type: mozilla-foundation/common_voice_11_0
      config: ro
      split: test
      args: ro
    metrics:
    - type: wer
      value: 4.73
      name: Wer
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: google/fleurs ro
      type: google/fleurs
      config: ro
      split: test
      args: ro
    metrics:
    - type: wer
      value: 19.64
      name: Wer
---

# Whisper Medium Romanian

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset, and the Romanian speech synthesis corpus.
It achieves the following results on the evaluation set:
- eval_loss: 0.06453
- eval_wer: 4.717
- epoch: 7.03
- step: 3500

## Model description

The architecture is the same as [openai/whisper-medium](https://huggingface.co/openai/whisper-medium).

## Training and evaluation data

The model was trained on the Common Voice 11.0 dataset (`train+validation+other` splits) and the Romanian speech synthesis corpus, and was tested on the `test` split of the Common Voice 11.0 dataset.

## Usage
Inference with 🤗 transformers
```python
from transformers import WhisperProcessor, WhisperForConditionalGeneration
from datasets import Audio, load_dataset
import torch

# load model and processor
processor = WhisperProcessor.from_pretrained("gigant/whisper-medium-romanian")
model = WhisperForConditionalGeneration.from_pretrained("gigant/whisper-medium-romanian")

# load dummy dataset and read soundfiles
ds = load_dataset("common_voice", "ro", split="test", streaming=True)
ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
input_speech = next(iter(ds))["audio"]["array"]
model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language = "ro", task = "transcribe")
input_features = processor(input_speech, return_tensors="pt", sampling_rate=16_000).input_features 
predicted_ids = model.generate(input_features, max_length=448)
# transcription = processor.batch_decode(predicted_ids)
transcription = processor.batch_decode(predicted_ids, skip_special_tokens = True)
```

The code was adapted from [openai/whisper-medium](https://huggingface.co/openai/whisper-medium).

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- 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