whisper-medium_ro-80mel β€” Romanian Fine-tune

Fine-tuned openai/whisper-medium on a merged Romanian corpus (~445h). Input: 80-mel spectrograms.

Performance (beam=5, full val)

Metric Value
WER 0.0656
CER 0.0228
Evaluated on 25,348 validation samples (52.75h).

Training

Parameter Value
Base openai/whisper-medium
GPU NVIDIA A100 80GB PCIe
Features 80-mel
Effective batch 128 (16Γ—8)
Optimizer adamw_torch
LR / scheduler 4e-06 / cosine
Warmup 500
Max epochs 8
Precision BF16
Selection eval_loss (early stop 5)
Date 2026-09-21

Dataset

Dataset Samples Hours
Echo 163,050 374.33h
VoxPopuli 27,060 85.20h
RODigits 15,389 37.55h
RO-Smart (TTS) 10,572 17.28h
CommonVoice-25 19,850 22.15h
FLEURS 4,161 13.73h
USPDATRO 2,637 4.31h
TOTAL 242,719 554.55h

Notes

  • decoder_start_token_id=50258 (SOT); positional label masking; begin_suppress_tokens=[220].
  • Checkpoint selection on eval_loss; final WER via standalone beam=5 generate.
Downloads last month
9
Safetensors
Model size
0.8B params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Evaluation results