| --- |
| language: |
| - ca |
| license: apache-2.0 |
| base_model: openai/whisper-tiny |
| tags: |
| - whisper-event |
| - generated_from_trainer |
| datasets: |
| - mozilla-foundation/common_voice_13_0 |
| metrics: |
| - wer |
| model-index: |
| - name: Whisper Tiny Catalan |
| results: |
| - task: |
| name: Automatic Speech Recognition |
| type: automatic-speech-recognition |
| dataset: |
| name: mozilla-foundation/common_voice_13_0 ca |
| type: mozilla-foundation/common_voice_13_0 |
| config: ca |
| split: test |
| args: ca |
| metrics: |
| - name: Wer |
| type: wer |
| value: 16.904258359531294 |
| --- |
| |
| # Whisper Tiny Catalan |
|
|
| ## Model summary |
|
|
| **Whisper Tiny Catalan** is an automatic speech recognition (ASR) model for **Catalan (ca)** speech. It is fine-tuned from [openai/whisper-tiny] on the **Catalan subset of Mozilla Common Voice 13.0**, achieving a **Word Error Rate (WER) of 16.90%** on the evaluation split. |
|
|
| This model is intended for general-purpose transcription of Catalan audio. |
|
|
| --- |
|
|
| ## Model description |
|
|
| * **Architecture:** Transformer-based encoder–decoder (Whisper) |
| * **Base model:** openai/whisper-tiny |
| * **Language:** Catalan (ca) |
| * **Task:** Automatic Speech Recognition (ASR) |
| * **Output:** Text transcription in Catalan |
| * **Decoding:** Autoregressive sequence-to-sequence decoding |
|
|
| Fine-tuned to improve transcription quality on Catalan audio, leveraging Whisper’s multilingual pretraining. |
|
|
| --- |
|
|
| ## Intended use |
|
|
| ### Primary use cases |
|
|
| * Transcription of Catalan audio recordings |
| * Offline or batch ASR pipelines |
| * Research and development in Catalan ASR |
| * Educational and media applications |
|
|
| ### Out-of-scope use |
|
|
| * Real-time or low-latency ASR without optimization |
| * Speech translation tasks |
| * Safety-critical applications without further validation |
|
|
| --- |
|
|
| ## Limitations and known issues |
|
|
| * Performance may degrade on: |
| * Noisy or low-quality recordings |
| * Conversational or spontaneous speech |
| * Dialects underrepresented in Common Voice |
| * Dataset biases may be reflected in outputs |
| * Occasional transcription errors can occur under difficult acoustic conditions |
|
|
| --- |
|
|
| ## Training and evaluation data |
|
|
| * **Dataset:** Mozilla Common Voice 13.0 (Catalan subset) |
| * **Data type:** Crowd-sourced, read speech |
| * **Preprocessing:** |
| * Audio resampled to 16 kHz |
| * Text normalized using Whisper tokenizer |
| * Filtering of invalid or problematic samples |
|
|
| * **Evaluation metric:** Word Error Rate (WER) on held-out evaluation set |
|
|
| --- |
|
|
| ## Evaluation results |
|
|
| | Metric | Value | |
| | ---------- | ---------- | |
| | WER (eval) | **16.90%** | |
|
|
| --- |
|
|
| ## Training procedure |
|
|
| ### Training hyperparameters |
|
|
| * Learning rate: 3.75e-5 |
| * Optimizer: Adam (β1=0.9, β2=0.999, ε=1e-8) |
| * LR scheduler: Linear |
| * Warmup steps: 500 |
| * Training steps: 5,000 |
| * Train batch size: 256 |
| * Eval batch size: 128 |
| * Seed: 42 |
|
|
| ### Training results (summary) |
|
|
| | Training Loss | Epoch | Step | Validation Loss | WER | |
| |:-------------:|:-----:|:----:|:---------------:|:-------:| |
| | 0.2098 | 7.02 | 1000 | 0.3994 | 22.5047 | |
| | 0.162 | 15.02 | 2000 | 0.3454 | 19.4181 | |
| | 0.0662 | 23.01 | 3000 | 0.3526 | 18.5687 | |
| | 0.0934 | 31.01 | 4000 | 0.3312 | 18.1600 | |
| | 0.1167 | 39.0 | 5000 | 0.3180 | 16.9043 | |
|
|
| --- |
|
|
| ## Framework versions |
|
|
| - Transformers 4.33.0.dev0 |
| - PyTorch 2.0.1+cu117 |
| - Datasets 2.14.4 |
| - Tokenizers 0.13.3 |
|
|
| --- |
|
|
| ## How to use |
|
|
| ```python |
| from transformers import pipeline |
| |
| hf_model = "HiTZ/whisper-tiny-ca" # replace with actual repo ID |
| device = 0 # set to -1 for CPU |
| |
| pipe = pipeline( |
| task="automatic-speech-recognition", |
| model=hf_model, |
| device=device |
| ) |
| |
| result = pipe("audio.wav") |
| print(result["text"]) |
| ``` |
|
|
| --- |
|
|
| ## Ethical considerations and risks |
|
|
| * This model transcribes speech and may process personal data. |
| * Users should ensure compliance with applicable data protection laws (e.g., GDPR). |
| * The model should not be used for surveillance or non-consensual audio processing. |
|
|
| --- |
|
|
| ## Citation |
|
|
| If you use this model in your research, please cite: |
|
|
| ```bibtex |
| @misc{dezuazo2025whisperlmimprovingasrmodels, |
| title={Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages}, |
| author={Xabier de Zuazo and Eva Navas and Ibon Saratxaga and Inma Hernáez Rioja}, |
| year={2025}, |
| eprint={2503.23542}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CL} |
| } |
| ``` |
|
|
| Please, check the related paper preprint in |
| [arXiv:2503.23542](https://arxiv.org/abs/2503.23542) |
| for more details. |
|
|
| --- |
|
|
| ## License |
|
|
| This model is available under the |
| [Apache-2.0 License](https://www.apache.org/licenses/LICENSE-2.0). |
| You are free to use, modify, and distribute this model as long as you credit |
| the original creators. |
|
|
| --- |
|
|
| ## Contact and attribution |
|
|
| * Fine-tuning and evaluation: HiTZ/Aholab - Basque Center for Language Technology |
| * Base model: OpenAI Whisper |
| * Dataset: Mozilla Common Voice |
|
|
| For questions or issues, please open an issue in the model repository. |
|
|
