Downloads · 30 days
0
Mathos34400/whisper-large-v3-turbo-french-v6
whisper-large-v3-turbo-french-v6 is a machine learning model from Mathos34400. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Fine-tuned version of openai/whisper-large-v3-turbo for French ASR using aggressive anti-overfitting strategies.
Downloads · 30 days
0
Access
Public
Updated Dec 15, 2025
Repo size
27.9 MB
Likes
1
Public
Click a slice to open those files.
.safetensors27.9 MB · 83%
From the Hugging Face model README
Fine-tuned version of openai/whisper-large-v3-turbo for French ASR using aggressive anti-overfitting strategies.
Average WER: 7.84% → 6.83% (-1.01pp, -12.9% improvement)
Evaluated with official Open ASR Leaderboard normalizer on 5 French datasets.
| Dataset | Base Model | Fine-tuned V6 | Improvement | Status |
|---|---|---|---|---|
| VoxPopuli | 12.11% | 8.88% | -3.23pp (-27%) | 🚀 Excellent |
| CommonVoice | 7.57% | 5.12% | -2.45pp (-32%) | 🚀 Excellent |
| TEDx | 8.52% | 8.58% | -0.06pp (-0.7%) | ≈ Neutral |
| MLS | 5.61% | 5.58% | +0.03pp (+0.5%) | ≈ Neutral |
| FLEURS | 5.41% | 6.01% | -0.60pp (-11%) | ⚠️ Regression |

✅ Strong improvements on VoxPopuli (-27%) and CommonVoice (-32%)
⚠️ FLEURS regression - Model optimized for European French accents, not African accents
≈ TEDx and MLS neutral (~0% change)
📊 3,176 samples evaluated across 5 datasets
This version addresses overfitting issues observed in V5 through multiple strategies:
Carefully selected subset focusing on generalization:
Total: 97k samples (vs 122k in V5, -19%)
from transformers import WhisperProcessor, WhisperForConditionalGeneration from peft import PeftModel import torch
Load model processor = WhisperProcessor.from_pretrained("Mathos34400/whisper-large-v3-turbo-french-v6") base_model = WhisperForConditionalGeneration.from_pretrained( "openai/whisper-large-v3-turbo", torch_dtype=torch.float16, device_map="auto" ) model = PeftModel.from_pretrained(base_model, "Mathos34400/whisper-large-v3-turbo-french-v6")
Inference audio = ... # 16kHz numpy array inputs = processor(audio, sampling_rate=16000, return_tensors="pt").to("cuda") generated_ids = model.generate(inputs["input_features"]) transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)
Result: Average WER improved from 8.33% → 6.83% (-1.50pp, -18%)
| Metric | V5 | V6 | Change |
|---|---|---|---|
| VoxPopuli | 13.24% | 8.88% | ✅ -4.36pp |
| CommonVoice | N/A | 5.12% | ✅ New |
| FLEURS | 6.25% | 6.01% | ✅ -0.24pp |
| MLS | 5.50% | 5.58% | ≈ +0.08pp |
| Average | 8.33% | 6.83% | ✅ -1.50pp |
@misc{whisper-french-v6, author = {Mathis Lacombe}, title = {Whisper Large v3 Turbo French V6 - Anti-Overfitting}, year = {2025}, publisher = {Hugging Face}, howpublished = {https://huggingface.co/Mathos34400/whisper-large-v3-turbo-french-v6} }
Apache 2.0
Model Card Authors: Mathis Lacombe
Evaluation Date: December 2025
Evaluation Method: Official Open ASR Leaderboard normalizer