File size: 2,550 Bytes
b6e8173 b8e666a b6e8173 756f5e3 b6e8173 272640c b6e8173 2525fcd b6e8173 |
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 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
import gradio as gr
import outetts
from outetts.models.config import GenerationConfig
from huggingface_hub import hf_hub_download, login
import os
import numpy as np
login(token=os.environ.get("HF_TOKEN"))
model_path = hf_hub_download(
repo_id="KandirResearch/DarijaTTS-v0.1-500M",
filename="unsloth.Q8_0.gguf",
)
model_config = outetts.GGUFModelConfig_v2(
model_path=model_path,
tokenizer_path="Lyte/DarijaTTS",
#verbose=False
)
interface = outetts.InterfaceGGUF(model_version="0.3", cfg=model_config)
# TTS function
def tts(text, temperature, repetition_penalty):
try:
gen_cfg = GenerationConfig(
text=text,
temperature=temperature,
repetition_penalty=repetition_penalty,
max_length=4096,
speaker=None
)
output = interface.generate(config=gen_cfg)
output_path = "output.wav"
output.save(output_path)
return output_path
except Exception as e:
raise gr.Error(f"Error generating audio: {str(e)}")
with gr.Blocks() as demo:
gr.Markdown("# Darija TTS Demo (alpha)")
gr.Markdown("### Note: this is an early alpha which still needs training. for now temperature 0.3 seems to work best, but feel free to play with it.")
with gr.Row():
text_input = gr.Textbox(
label="Enter text for TTS",
value="السلام كيداير لاباس عليك؟"
)
output_audio = gr.Audio(label="Generated Audio", type="filepath")
generate_btn = gr.Button("Generate Audio")
with gr.Row():
temperature = gr.Slider(
minimum=0.01,
maximum=1.0,
value=0.3,
step=0.01,
label="Temperature"
)
repetition_penalty = gr.Slider(
minimum=0.8,
maximum=1.5,
value=1.1,
step=0.05,
label="Repetition Penalty"
)
with gr.Row():
gr.Markdown("### Examples:")
with gr.Row():
gr.Examples(
[
["رمضان مبارك سعيد"],
["اشنو بان ليك فهادشي مزيان؟"],
["السلام كيداير لاباس عليك؟"],
["واش كاين شي جديد اليوم؟"]
],
inputs=[text_input])
generate_btn.click(
fn=tts,
inputs=[text_input, temperature, repetition_penalty],
outputs=output_audio
)
demo.launch(debug=True) |