Spaces:
Running
Running
File size: 9,145 Bytes
2f29448 7683895 2add214 2f29448 2add214 2f29448 2add214 85d8a82 2add214 2f29448 2add214 2f29448 7683895 2f29448 7683895 2f29448 3dc4140 7683895 3dc4140 7683895 2f29448 3a5211e 2f29448 3a5211e 2f29448 3dc4140 2f29448 7683895 2f29448 adf12f4 e55f2bb adf12f4 7683895 2f29448 7683895 adf12f4 7683895 2f29448 adf12f4 2f29448 3dc4140 2f29448 |
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 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 |
import gradio as gr
import numpy as np
import torch
import random
from diffusers import DiffusionPipeline
from datasets import load_dataset
from transformers import SpeechT5ForTextToSpeech, SpeechT5HifiGan, SpeechT5Processor, pipeline
device = "cuda:0" if torch.cuda.is_available() else "cpu"
title = "GenAI StoryTeller"
description = """
Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for Speech Translation,
Microsoft's[SpeechT5 TTS](https://huggingface.co/microsoft/speecht5_tts) model for Text-to-Speech and
StabilityAI's [StableDiffusion](https://huggingface.co/stabilityai/sdxl-turbo) model for Image Generation
"""
# Load speech translation pipeline
asr_pipe = pipeline("automatic-speech-recognition", model="openai/whisper-base", device=device)
# Load text-to-speech processor from pretrained dataset
processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts").to(device)
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan").to(device)
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# Load diffusion pipeline for image generation
if torch.cuda.is_available():
torch.cuda.max_memory_allocated(device=device)
pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
pipe.enable_xformers_memory_efficient_attention()
pipe = pipe.to(device)
else:
pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
pipe = pipe.to(device)
if torch.cuda.is_available():
power_device = "GPU"
else:
power_device = "CPU"
# Limit the file size
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
# Speech GenAI
# Function for translating different language using pretrained models
def translate(audio):
outputs = asr_pipe(audio, max_new_tokens=256, generate_kwargs={"task": "translate"})
return outputs["text"]
# Function to synthesise the text using the processor above
def synthesise(text):
inputs = processor(text=text, return_tensors="pt")
speech = model.generate_speech(inputs["input_ids"].to(device), speaker_embeddings.to(device), vocoder=vocoder)
return speech.cpu()
# Main function
def speech_to_speech_translation(audio):
translated_text = translate(audio)
synthesised_speech = synthesise(translated_text)
synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
return 16000, synthesised_speech
# Function for text to speech
def text_to_speech(text):
synthesised_speech = synthesise(text)
synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
return 16000, synthesised_speech
# Image GenAI
# Text to Image
def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
image = pipe(
prompt = prompt,
negative_prompt = negative_prompt,
guidance_scale = guidance_scale,
num_inference_steps = num_inference_steps,
width = width,
height = height,
generator = generator
).images[0]
return image
examples = [
"Dog licking ice cream",
]
# CSS
'''css="""
#col-container {
margin: 0 auto;
max-width: 520px;
}
"""'''
demo = gr.Blocks()
# Audio translation using microphone as the input
audio_translate = gr.Interface(
fn=speech_to_speech_translation,
inputs=gr.Audio(source="microphone", type="filepath"),
outputs=gr.Audio(label="Generated Speech", type="numpy"),
title=title,
description=description,
)
# File translation using uploaded files as input
file_translate = gr.Interface(
fn=speech_to_speech_translation,
inputs=gr.Audio(source="upload", type="filepath"),
outputs=gr.Audio(label="Generated Speech", type="numpy"),
examples=[["./english.wav"], ["./chinese.wav"]],
title=title,
description=description,
)
# Text translation using text as input
text_translate = gr.Interface(
fn=text_to_speech,
inputs="textbox",
outputs=gr.Audio(label="Generated Speech", type="numpy"),
title=title,
description=description
)
# Inputs for Image Generation
prompt = gr.Text(
label="Prompt",
show_label=False,
max_lines=1,
placeholder="Enter your prompt",
container=False,
)
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
visible=False,
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=0,
)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
width = gr.Slider(
label="Width",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512,
)
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=10.0,
step=0.1,
value=0.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=12,
step=1,
value=2,
)
result = gr.Image(label="Result", show_label=False)
'''with gr.Blocks(css=css) as image:
with gr.Column(elem_id="col-container"):
gr.Markdown(f"""
# Text-to-Image
Currently running on {power_device}.
""")
with gr.Row():
prompt = gr.Text(
label="Prompt",
show_label=False,
max_lines=1,
placeholder="Enter your prompt",
container=False,
)
run_button = gr.Button("Run", scale=0)
result = gr.Image(label="Result", show_label=False)
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
visible=False,
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=0,
)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
with gr.Row():
width = gr.Slider(
label="Width",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512,
)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=10.0,
step=0.1,
value=0.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=12,
step=1,
value=2,
)
gr.Examples(
examples = examples,
inputs = [prompt]
)
run_button.click(
fn = infer,
inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
outputs = [result]
)
'''
# Text to Image interface
image_generation = gr.Interface(
fn=infer,
inputs=[prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
outputs=[result],
title=title,
description=description,
)
# Showcase the demo using different tabs of the different features
with demo:
gr.TabbedInterface([audio_translate, file_translate, text_translate, image_generation], ["Speech to Text", "Audio to Text", "Text to Speech", "Text to Image"])
demo.launch() |