Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 language:
   - yo
-license: cc-by-4.0
+license: cc-by-nc-4.0
 tags:
   - text-to-speech
   - tts
@@ -24,6 +24,7 @@ Fine-tuned [F5-TTS v1 Base](https://github.com/SWivid/F5-TTS) (335M params) for
 - **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
 
@@ -42,12 +43,12 @@ Fine-tuned [F5-TTS v1 Base](https://github.com/SWivid/F5-TTS) (335M params) for
 ## Usage
 
 ```python
-from f5_tts.api import F5TTS
 import f5_tts.model.utils as f5_utils
-
-# CRITICAL: Bypass pinyin conversion before importing
+# 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",
@@ -55,18 +56,28 @@ f5tts = F5TTS(
     device="cuda",
 )
 
-# ref_file: 5-10s WAV of any voice
+# 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=0.85,
+    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 |
@@ -78,17 +89,29 @@ wav, sr, _ = f5tts.infer(
 ## Limitations
 
 - Tonal minimal pair differentiation is moderate (not perfect for all tone contrasts)
-- Works best with female voices (majority of training data)
+- 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-4.0 (following BibleTTS and SLR86 licenses)
+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},
@@ -96,3 +119,7 @@ CC-BY-4.0 (following BibleTTS and SLR86 licenses)
   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).