| --- |
| language: |
| - yo |
| license: cc-by-nc-4.0 |
| tags: |
| - text-to-speech |
| - tts |
| - f5-tts |
| - yoruba |
| - african-languages |
| - voice-cloning |
| - zero-shot-tts |
| library_name: f5-tts |
| pipeline_tag: text-to-speech |
| --- |
| |
| # F5-TTS Yorùbá — First Zero-Shot Voice Cloning TTS for Yorùbá |
|
|
| Fine-tuned [F5-TTS v1 Base](https://github.com/SWivid/F5-TTS) (335M params) for Yorùbá language with full tonal diacritic support. |
|
|
| ## Highlights |
|
|
| - **Zero-shot voice cloning**: Clone any voice from a 5-10 second reference clip |
| - **Tonal language support**: Diacritic-driven pitch generation (ẹ́, ọ̀, ṣ, etc.) |
| - **First of its kind**: First DiT-based / flow-matching TTS model for any African language |
| - **Character-level tokenization**: No phonemizer needed — raw Yorùbá text with diacritics in, speech out |
| - **Fast inference**: ~350ms per utterance at NFE=16 on L4 GPU (RTF ≈ 0.15) |
|
|
| ## Training Details |
|
|
| | | | |
| |---|---| |
| | Base model | F5-TTS v1 Base (flow-matching DiT) | |
| | Parameters | 335M | |
| | Training data | ~13.4 hours (BibleTTS + SLR86 + WAXAL) | |
| | Steps | 150,000 | |
| | GPUs | 2× A100-40GB | |
| | Effective batch | 38,400 frames/step | |
| | Learning rate | 7.5e-5 | |
| | Tokenizer | Character-level (no pinyin) | |
| | Vocab | 2,562 chars (base + Yorùbá diacritics) | |
|
|
| ## Usage |
|
|
| ```python |
| import f5_tts.model.utils as f5_utils |
| # CRITICAL: Must bypass pinyin conversion BEFORE any other F5-TTS import |
| f5_utils.convert_char_to_pinyin = lambda texts, polyphone=True: texts |
| |
| from f5_tts.api import F5TTS |
| |
| f5tts = F5TTS( |
| model="F5TTS_v1_Base", |
| ckpt_file="model_150000.pt", |
| vocab_file="vocab.txt", |
| device="cuda", |
| ) |
| |
| # ref_file: 5-10s WAV of any voice (add ~1s trailing silence for best results) |
| # ref_text: what the reference says (Yorùbá or English) |
| # gen_text: Yorùbá text with full diacritics |
| wav, sr, _ = f5tts.infer( |
| ref_file="reference.wav", |
| ref_text="text spoken in reference", |
| gen_text="ẹ kú àárọ̀, báwo ni àwọn ọmọ yín ṣe wà?", |
| speed=1.0, |
| nfe_step=16, |
| file_wave="output.wav", |
| ) |
| ``` |
|
|
| ### Tips for Best Results |
|
|
| - **Use full diacritics**: "oko" (hoe), "okó" (husband), "okò" (vehicle) are different words. Diacritics drive pitch. |
| - **Reference audio**: Use clean 5-10 second clips with ~1 second of trailing silence. Avoid background music/noise. |
| - **Reference text**: Must accurately match what is spoken in the reference audio. |
| - **NFE steps**: 16 recommended for best quality/speed tradeoff. Use 8 for faster inference with slight quality reduction. |
| - **Speed**: 1.0 recommended. Lower values (e.g. 0.85) may prevent truncation on long text but can cause slight shakiness. |
| - **Text cleanup**: Strip any bracket tags (e.g. `[breath]`, `[snap]`) from reference text if present. |
|
|
| ## Training Data |
|
|
| | Source | Samples | Hours | Notes | |
| |--------|---------|-------|-------| |
| | [BibleTTS Yorùbá](https://masakhane-io.github.io/bibleTTS/) | 7,560 | ~8h | Studio quality, single speaker | |
| | [SLR86](https://openslr.org/86/) | 3,583 | ~3h | Crowdsourced, male + female | |
| | [WAXAL TTS](https://huggingface.co/datasets/google/WaxalNLP) | 1,492 | ~3h | Diacritics restored via Gemini | |
|
|
| ## Limitations |
|
|
| - Tonal minimal pair differentiation is moderate (not perfect for all tone contrasts) |
| - Occasional brief audio artifacts (~5% of generations) — regenerating typically produces a clean output |
| - Reference audio may bleed slightly into the start of generated audio — trimming the first 200-400ms helps |
| - Requires full Yorùbá diacritics in input text for best results |
| - Reference audio quality directly affects output quality |
|
|
| ## What's Next |
|
|
| - Phase 2 tonal fine-tuning (oversampled minimal pairs) |
| - Hausa and Igbo models using the same pipeline |
| - Nigerian Pidgin (non-tonal, simpler) |
| - Edge-optimized smaller model for on-device inference |
|
|
| ## License |
|
|
| CC-BY-NC-4.0 |
|
|
| This model is free for research and non-commercial use. For commercial licensing, contact us. |
|
|
| The base F5-TTS pretrained model is licensed under CC-BY-NC due to the Emilia training dataset. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @misc{naijaml-f5tts-yoruba-2026, |
| title={F5-TTS Yorùbá: First Zero-Shot Voice Cloning TTS for Yorùbá}, |
| author={NaijaML}, |
| year={2026}, |
| url={https://huggingface.co/naijaml/f5-tts-yoruba} |
| } |
| ``` |
|
|
| ## Acknowledgments |
|
|
| Built on [F5-TTS](https://github.com/SWivid/F5-TTS) by Yushen Chen et al. Training data from [BibleTTS](https://masakhane-io.github.io/bibleTTS/), [SLR86](https://openslr.org/86/), and [Google WAXAL](https://huggingface.co/datasets/google/WaxalNLP). |
