Update README.md

README.md

@@ -11,11 +11,11 @@ base_model:
 - facebook/mms-tts-div
 ---
 
-# 🎙️ Divehi TTS – Male Voice (VITS-based)
+# Divehi TTS – Male Voice (VITS-based)
 
 This is a fine-tuned VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) model for Divehi speech synthesis. The model produces Male voice audio from Thaana-scripted Divehi text. Fine-tuned from Meta’s MMS-TTS architecture using a curated dataset of synthetic Divehi speech.
 
-## 🧠 Model Details
+## Model Details
 
 | Field                 | Value                                           |
 |----------------------|-------------------------------------------------|
@@ -28,7 +28,7 @@ This is a fine-tuned VITS (Variational Inference with adversarial learning for e
 | **Inference Engine** | Transformers (🤗 Hugging Face)                  |
 
 
-## 🚀 Usage
+## Usage
 
 ```python
 from transformers import VitsModel, VitsTokenizer
@@ -44,7 +44,7 @@ waveform = model.generate(**inputs).waveform[0]
 torchaudio.save("output.wav", waveform.unsqueeze(0), 16000)
 ```
 
-## 📊 Evaluation Summary
+## Evaluation Summary
 
 - **Model**: `alakxender/mms-tts-div-finetuned-md-m02`
 - **Evaluated Samples**: 3
@@ -64,7 +64,7 @@ torchaudio.save("output.wav", waveform.unsqueeze(0), 16000)
   - 📄 Report: `outputs/report.txt`
   - 📈 MOS Scores: `outputs/mos_scores.txt`
 
-## 🙏 Acknowledgements
+## Acknowledgements
 
 - [Meta MMS-TTS](https://github.com/facebookresearch/fairseq/tree/main/examples/mms)
 - [Tarepan's SpeechMOS](https://github.com/Tarepan/SpeechMOS)