File size: 2,553 Bytes
10ea2f8 393129e 10ea2f8 393129e 10ea2f8 |
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 62 63 64 65 66 67 68 69 70 71 |
"""
Chiluka TTS - HuggingFace Hub Example
Load model weights directly from HuggingFace Hub.
No need to clone the repository or download weights manually.
Requirements:
pip install chiluka
sudo apt-get install espeak-ng
Usage:
python huggingface_example.py --reference path/to/reference.wav
python huggingface_example.py --reference ref.wav --model telugu --language te --text "నమస్కారం"
"""
import argparse
from chiluka import Chiluka, list_models
def main():
parser = argparse.ArgumentParser(description="Chiluka TTS - HuggingFace Hub Example")
parser.add_argument("--reference", type=str, required=True, help="Path to reference audio file")
parser.add_argument("--model", type=str, default="hindi_english", choices=["hindi_english", "telugu"],
help="Model variant to use (default: hindi_english)")
parser.add_argument("--text", type=str, default=None, help="Text to synthesize")
parser.add_argument("--language", type=str, default=None, help="Language code (en-us, hi, te)")
parser.add_argument("--output", type=str, default="output_hf.wav", help="Output wav file path")
parser.add_argument("--device", type=str, default=None, help="Device: cuda or cpu")
args = parser.parse_args()
# Show available models
print("Available models:")
for name, info in list_models().items():
marker = " <--" if name == args.model else ""
print(f" {name}: {info['description']}{marker}")
print()
# Set defaults based on model choice
if args.text is None:
if args.model == "telugu":
args.text = "నమస్కారం, నేను చిలుక మాట్లాడుతున్నాను"
else:
args.text = "Hello, I am Chiluka, a text to speech system."
if args.language is None:
if args.model == "telugu":
args.language = "te"
else:
args.language = "en-us"
# Load model from HuggingFace Hub (auto-downloads on first use)
print(f"Loading '{args.model}' model from HuggingFace Hub...")
tts = Chiluka.from_pretrained(model=args.model, device=args.device)
# Synthesize
print(f"Synthesizing: '{args.text}'")
print(f"Language: {args.language}")
wav = tts.synthesize(
text=args.text,
reference_audio=args.reference,
language=args.language,
)
# Save
tts.save_wav(wav, args.output)
print(f"Duration: {len(wav) / 24000:.2f} seconds")
if __name__ == "__main__":
main()
|