Spaces:
Configuration error
Configuration error
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,50 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Myanmar Text-to-Speech Demo
|
| 2 |
+
|
| 3 |
+
This Hugging Face Space demonstrates the Myanmar Text-to-Speech (TTS) system developed by [hpbyte](https://github.com/hpbyte/myanmar-tts). It's an end-to-end speech synthesis system specifically designed for the Burmese language.
|
| 4 |
+
|
| 5 |
+
## About the Project
|
| 6 |
+
|
| 7 |
+
This is an implementation of Tacotron 2 for Myanmar language text-to-speech synthesis. Unlike Meta's Massively Multilingual Speech (MMS) Burmese TTS, this project is specifically focused on high-quality Burmese speech synthesis using an end-to-end approach.
|
| 8 |
+
|
| 9 |
+
### Key Features:
|
| 10 |
+
- End-to-end Burmese text-to-speech synthesis
|
| 11 |
+
- Built on the Tacotron 2 architecture
|
| 12 |
+
- Custom text processing for the Myanmar language
|
| 13 |
+
- Clean and natural-sounding voice output
|
| 14 |
+
|
| 15 |
+
## How to Use This Demo
|
| 16 |
+
|
| 17 |
+
1. Enter Burmese text in the input box
|
| 18 |
+
2. Click "Submit" to generate speech
|
| 19 |
+
3. Listen to the generated audio output
|
| 20 |
+
|
| 21 |
+
## Examples
|
| 22 |
+
|
| 23 |
+
Try these example phrases:
|
| 24 |
+
- မင်္ဂလာပါ (Hello)
|
| 25 |
+
- မြန်မာစကားပြောစနစ်ကို ကြိုဆိုပါတယ် (Welcome to the Myanmar speech system)
|
| 26 |
+
- ဒီစနစ်ဟာ မြန်မာစာကို အသံအဖြစ် ပြောင်းပေးနိုင်ပါတယ် (This system can convert Myanmar text to speech)
|
| 27 |
+
|
| 28 |
+
## Model Details
|
| 29 |
+
|
| 30 |
+
This model uses a Tacotron 2 architecture to generate mel spectrograms from text, which are then converted to waveforms using a vocoder. The model was trained on a dataset of Burmese speech.
|
| 31 |
+
|
| 32 |
+
## References
|
| 33 |
+
|
| 34 |
+
- Original Repository: [https://github.com/hpbyte/myanmar-tts](https://github.com/hpbyte/myanmar-tts)
|
| 35 |
+
- Paper: [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://arxiv.org/abs/1712.05884)
|
| 36 |
+
|
| 37 |
+
## Citation
|
| 38 |
+
|
| 39 |
+
If you use this model in your research or application, please cite the original repository:
|
| 40 |
+
|
| 41 |
+
```
|
| 42 |
+
@misc{myanmar-tts,
|
| 43 |
+
author = {Htet Pyie Sone},
|
| 44 |
+
title = {Myanmar Text-to-Speech},
|
| 45 |
+
year = {2021},
|
| 46 |
+
publisher = {GitHub},
|
| 47 |
+
journal = {GitHub repository},
|
| 48 |
+
howpublished = {\url{https://github.com/hpbyte/myanmar-tts}}
|
| 49 |
+
}
|
| 50 |
+
```
|