--- license: apache-2.0 language: - nl base_model: openai/whisper-tiny tags: - automatic-speech-recognition - whisper - dutch - speech - audio - synthetic-data - asr - hf-asr-leaderboard datasets: - mozilla-foundation/common_voice_17_0 - yuriyvnv/synthetic_transcript_nl model-index: - name: whisper-tiny-mixed-nl results: - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: Common Voice 17.0 (Dutch) type: mozilla-foundation/common_voice_17_0 config: nl split: test metrics: - type: wer value: 25.05 name: Test WER - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: Multilingual LibriSpeech (Dutch) type: facebook/multilingual_librispeech config: dutch split: test metrics: - type: wer value: 43.11 name: Test WER (MLS) pipeline_tag: automatic-speech-recognition library_name: transformers --- # Whisper-Tiny Dutch - Mixed Synthetic Data (Mid-High Quality Filtered) This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) for Dutch automatic speech recognition (ASR). It was trained on Common Voice 17.0 Dutch combined with **WAVe-filtered synthetic speech data** (quality threshold q ≥ 0.5). ## Introduction ### How the Data Was Created The training data combines real speech from Common Voice 17.0 with synthetic speech generated through a two-stage pipeline: 1. **Transcript Generation**: We used GPT-4o-mini to generate Dutch transcripts that match the word count distribution observed in Common Voice, ensuring realistic utterance lengths and diverse linguistic content. 2. **Speech Synthesis**: Each transcript was converted to audio using OpenAI's TTS-1 model with 9 different voice variants (alloy, ash, coral, echo, fable, nova, onyx, sage, shimmer), producing 34,898 synthetic samples. 3. **Quality Filtering with WAVe**: Raw synthetic speech often contains defects such as mispronunciations, omitted words, or prosodic anomalies. To address this, we applied **WAVe (Word-Aligned Verification)**, a model that assesses audio-text alignment at the word level rather than the sentence level. WAVe uses multi-head attention to align each word to its corresponding audio frames and assigns per-word confidence scores via a GLU-based scorer. Samples scoring below the threshold (q < 0.5) were removed, retaining 30,182 high-quality synthetic samples. ### How the Model Was Created The model was fine-tuned from `openai/whisper-tiny` using the Hugging Face Transformers library with the following approach: 1. **Mixed Training**: Combined 34,952 real speech samples from Common Voice 17.0 Dutch with 30,182 WAVe-filtered synthetic samples (65,134 total). 2. **Optimization**: Trained for 5 epochs with a learning rate of 5e-5, global batch size of 256, and BF16 precision on an NVIDIA H200 GPU. 3. **Checkpoint Selection**: The best checkpoint was selected based on validation loss, occurring at step 1000 with a validation loss of 0.3292. This approach achieves **3.7% relative improvement** on the Common Voice test set compared to training on real data alone, while also improving cross-domain generalization on the Multilingual LibriSpeech benchmark. ## Model Details | Property | Value | |----------|-------| | **Base Model** | openai/whisper-tiny | | **Language** | Dutch (nl) | | **Task** | Automatic Speech Recognition (transcribe) | | **Parameters** | 39M | | **Training Data** | Common Voice 17.0 + Mid-High Quality Synthetic | | **Total Training Samples** | 65,134 | | **Sampling Rate** | 16kHz | ## Evaluation Results ### This Model (whisper-tiny-mixed-nl) | Metric | Value | |--------|-------| | **Validation Loss** | 0.3292 | | **Validation WER** | 19.36% | | **Test WER (Common Voice)** | 25.05% | | **Test WER (MLS)** | 43.11% | | **Best Checkpoint** | Step 1000 | | **Max Training Steps** | 1,270 | ### Comparison with Other Training Configurations | Training Data | Max Steps | Val Loss | Val WER | Test WER (CV) | Test WER (MLS) | |---------------|-----------|----------|---------|---------------|----------------| | Common Voice Only | 680 | 0.3382 | 19.77% | 26.00% | 44.85% | | High-Quality Filtered + CV | 890 | 0.3323 | 19.59% | 25.51% | 43.76% | | **Mid-High Quality Filtered + CV** | **1,270** | **0.3292** | **19.36%** | **25.05%** | **43.11%** | | All Synthetic + CV (Unfiltered) | 1,365 | 0.3207 | 19.61% | 24.93% | 43.12% | ### Key Performance Highlights - **Best Validation WER** (19.36%) among all Whisper-Tiny Dutch configurations - **Best cross-domain generalization** on MLS benchmark (43.11% WER) - **3.7% relative improvement** on Common Voice test set vs baseline (25.05% vs 26.00%) - **7% fewer training steps** than unfiltered synthetic data while achieving better generalization ## Training Data ### Dataset Composition | Source | Samples | Description | |--------|---------|-------------| | [Common Voice 17.0 Dutch](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0) | 34,952 | Real speech from Mozilla's crowdsourced dataset | | [Synthetic Transcript NL](https://huggingface.co/datasets/yuriyvnv/synthetic_transcript_nl) (q ≥ 0.5) | 30,182 | WAVe-filtered TTS audio from GPT-4o-mini transcripts | | **Total** | **65,134** | | ### Synthetic Data Generation Pipeline The synthetic dataset ([yuriyvnv/synthetic_transcript_nl](https://huggingface.co/datasets/yuriyvnv/synthetic_transcript_nl)) was generated using: 1. **Transcript Generation**: GPT-4o-mini, matching Common Voice word count distribution 2. **Speech Synthesis**: OpenAI TTS-1 model with 9 voice variants (alloy, ash, coral, echo, fable, nova, onyx, sage, shimmer) 3. **Quality Filtering**: WAVe model filtering at threshold q ≥ 0.5 ### WAVe Quality Distribution (Dutch Synthetic Data) | Quality Level | Samples | Percentage | |--------------|---------|------------| | High (q ≥ 0.8) | 10,555 | 30.2% | | Medium (0.5 ≤ q < 0.8) | 19,627 | 56.2% | | Low (q < 0.5) - Removed | 4,716 | 13.5% | ## Training Procedure ### Hyperparameters | Parameter | Value | |-----------|-------| | Learning Rate | 5e-5 | | Batch Size (Global) | 256 | | Warmup Steps | 200 | | Max Epochs | 5 | | Precision | BF16 | | Optimizer | AdamW (fused) | | Eval Steps | 50 | | Metric for Best Model | eval_loss | ### Training Infrastructure - **GPU**: NVIDIA H200 (140GB VRAM) - **Operating System**: Ubuntu 22.04 - **Framework**: Hugging Face Transformers ### Training Curve ``` Step 100: val_loss = 0.5209 Step 250: val_loss = 0.3979 Step 500: val_loss = 0.3454 Step 750: val_loss = 0.3300 Step 1000: val_loss = 0.3292 ← Best checkpoint Step 1250: val_loss = 0.3334 ``` ## Usage ### Transcription Pipeline ```python from transformers import pipeline transcriber = pipeline( "automatic-speech-recognition", model="yuriyvnv/whisper-tiny-mixed-nl", device="cuda" ) result = transcriber("path/to/dutch_audio.wav") print(result["text"]) ``` ### Direct Model Usage ```python from transformers import WhisperProcessor, WhisperForConditionalGeneration import librosa processor = WhisperProcessor.from_pretrained("yuriyvnv/whisper-tiny-mixed-nl") model = WhisperForConditionalGeneration.from_pretrained("yuriyvnv/whisper-tiny-mixed-nl") model.to("cuda") audio, sr = librosa.load("path/to/dutch_audio.wav", sr=16000) input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features.to("cuda") predicted_ids = model.generate(input_features) transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0] print(transcription) ``` ### Specifying Language ```python model.generation_config.language = "nl" model.generation_config.task = "transcribe" ``` ## Methodology This model leverages **WAVe (Word-Aligned Verification)**, a word-level quality assessment method for filtering synthetic speech data. Unlike sentence-level filtering approaches, WAVe: - Aligns each word to its corresponding audio frames using multi-head attention - Assigns per-word confidence scores via a GLU-based scorer - Detects localized synthesis errors (mispronunciations, omitted words, prosodic anomalies) - Achieves **6.5% improvement** over sentence-level filtering methods For full methodology details, see the references below. ## Limitations - **Model capacity**: Whisper-Tiny (39M params) has limited representational power - **Domain specificity**: Optimized for general Dutch; may underperform on technical domains - **Acoustic conditions**: Trained on clean speech; noise robustness not guaranteed - **Dialect coverage**: Performance may vary across Dutch regional variants ## Citation ```bibtex @article{perezhohin2024enhancing, title={Enhancing Automatic Speech Recognition: Effects of Semantic Audio Filtering on Models Performance}, author={Perezhohin, Yuriy and Santos, Tiago and Costa, Victor and Peres, Fernando and Castelli, Mauro}, journal={IEEE Access}, year={2024}, publisher={IEEE} } @article{perezhohin2026wave, title={WAVe: Word-aligned verification of synthetic speech for ASR}, author={Perezhohin, Yuriy and Castelli, Mauro}, journal={Information Sciences}, pages={123591}, year={2026}, publisher={Elsevier} } ``` ## References - **Base Model**: [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) - **Training Data (Real)**: [mozilla-foundation/common_voice_17_0](https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0) - **Training Data (Synthetic)**: [yuriyvnv/synthetic_transcript_nl](https://huggingface.co/datasets/yuriyvnv/synthetic_transcript_nl) - **Whisper Paper**: [Robust Speech Recognition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356) - **IEEE Access Paper**: [Enhancing ASR with Semantic Audio Filtering](https://ieeexplore.ieee.org/document/10720758) ## License Apache 2.0