Downloads · 30 days
43
31% of all-time downloads
whisper-large-v3-turbo-ro
IonGrozea/whisper-large-v3-turbo-ro
whisper-large-v3-turbo-ro is a automatic speech recognition model from IonGrozea. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Fine-tuned openai/whisper-large-v3-turbo on a merged Romanian speech corpus (128-mel input features).
All-time downloads
138
Public
Repo size
9.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jun 10, 2026
- Updated
- Aug 22, 2026
- SHA
- 914e1292
Model card
From the Hugging Face model README
whisper-large-v3-turbo-ro — Romanian Fine-tune
Fine-tuned openai/whisper-large-v3-turbo
on a merged Romanian speech corpus (128-mel input features).
Performance
| Metric | Normalized | Raw |
|---|---|---|
| WER | 0.063 | 0.0659 |
| CER | 0.0208 | 0.0214 |
Normalized = lowercased, punctuation stripped (comparable to Whisper papers). Evaluated on 2000 validation samples, beam=5.
Metrics read from eval_results.json.
Usage
from transformers import WhisperProcessor, WhisperForConditionalGeneration
import torch
processor = WhisperProcessor.from_pretrained("IonGrozea/whisper-large-v3-turbo-ro")
model = WhisperForConditionalGeneration.from_pretrained("IonGrozea/whisper-large-v3-turbo-ro")
inputs = processor(audio_array, sampling_rate=16000, return_tensors="pt")
with torch.no_grad():
ids = model.generate(inputs.input_features, language="romanian",
task="transcribe", num_beams=5)
print(processor.batch_decode(ids, skip_special_tokens=True)[0])
This card was auto-generated at upload time because the source folder had no
README.md (e.g. a raw checkpoint). For the full training-config card, upload
from the final_best/ directory instead.
- Task
- Automatic Speech Recognition
- Type
- whisper
- License
- apache-2.0
- Languages
- ro
- Created
- Jun 10, 2026
- Updated
- Aug 22, 2026