File size: 1,773 Bytes
2599fe1 34e9dff 586874b 34e9dff |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
---
tags:
- audio
- text-to-speech
language: kbd
license: mit
datasets:
- anzorq/kbd_speech
pipeline_tag: text-to-speech
---
# KBD TTS Male Model
## Install dependencies
```bash
pip install git+https://github.com/coqui-ai/TTS@dev#egg=TTS`
pip install gradio`
```
## Usage
```python
import os
from TTS.utils.download import download_url
from TTS.utils.synthesizer import Synthesizer
import tempfile
def download_model_and_config():
dir_path = "kbd-vits-tts"
if not os.path.exists(dir_path):
os.makedirs(dir_path)
model_url = "https://huggingface.co/anzorq/kbd-vits-tts-male/resolve/main/checkpoint_56000.pth"
config_url = "https://huggingface.co/anzorq/kbd-vits-tts-male/resolve/main/config_35000.json"
download_url(model_url, dir_path, "model.pth")
download_url(config_url, dir_path, "config.json")
return dir_path
model_dir = download_model_and_config()
def tts_male(text: str):
synthesizer = Synthesizer(f"{model_dir}/model.pth", f"{model_dir}/config.json")
text = text.replace("I", "ӏ") #replace capital 'i's with lowercase "Palochka" symbol
wavs = synthesizer.tts(text)
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
synthesizer.save_wav(wavs, fp)
return fp.name
text = "Гупсыси псалъэ, зыплъыхьи тIыс"
output_path = tts_male(text)
print(f"Generated audio saved at: {output_path}")
```
This will generate an audio file using the male model and save it to a temporary file. The path to the generated audio file will be printed.
**Note**
The model was trained on text with the lowercase palochka symbol.
Make sure to replace "I"s and similar symbols with "ӏ" (lowercase palochka symbol) in the input text, as shown in the provided code. |