README.md

---
license: agpl-3.0
metrics:
- wer
base_model:
- openai/whisper-large-v3-turbo
pipeline_tag: automatic-speech-recognition
tags:
- upper_sorbian
---


## Model Description

This model was fine-tuned on over 24 hours of transcribed upper sorbian speech to aid future research, conservation and revitalisation of the language.


## Training Data
- **Source:** Stiftung für das sorbische Volk / Załožba za serbski lud (https://stiftung.sorben.com/)
- **Volume:** 1493 Minutes, 10% Validation Set, 10% Test Set

## Training Details
- **Hyperparameters**: 
  - Batch size: 64
  - Learning rate: 3e-6, linear decay
- **Optimizer**: AdamW
- **Warmup**: 1000 steps
- **Additional Techniques**: BF16 training, initial 15 layers frozen


## Performance
### Metrics
- **Word Error Rate:** 6.2

## Usage
### Example Code

To use the model, follow this example code:

```python
import torch
import torchaudio
from transformers import WhisperProcessor, WhisperForConditionalGeneration

# Load the model and processor
model_name = "DILHTWD/whisper-large-v3-turbo-hsb"
processor_name = "openai/whisper-large-v3-turbo"
processor = WhisperProcessor.from_pretrained(processor_name)
model = WhisperForConditionalGeneration.from_pretrained(model_name)

# Load and preprocess the audio
audio, sample_rate = torchaudio.load("test.mp3")
if sample_rate != 16000:
    audio = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)(audio)
input_features = processor(audio.squeeze().numpy(), sampling_rate=16000, return_tensors="pt").input_features

# Generate transcription
with torch.no_grad():
    predicted_ids = model.generate(input_features)
    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]

# Print the transcription
print("Transcription:", transcription)
```

## Model Details
- **Model Name:** DILHTWD/whisper-large-v3-turbo-hsb
- **Publisher:** Data Intelligence Lab, Hochschule für Technik und Wirtschaft Dresden
- **Model Version:** 1.0.0
- **Model Date:** 2024-11-15
- **License:** [AGPL-3.0](https://www.gnu.org/licenses/agpl-3.0.de.html)
- **Architecture:** Whisper Large v3 Turbo
- **Task:** Automatic Speech Recognition