Spaces:
Running
Running
File size: 3,480 Bytes
667be37 a72ef71 667be37 a72ef71 667be37 a72ef71 667be37 a72ef71 667be37 a72ef71 667be37 b471af6 667be37 a72ef71 667be37 077bff1 667be37 a72ef71 667be37 a72ef71 44fa807 a72ef71 667be37 077bff1 |
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 |
import gradio as gr
import httpx
from gradio_dialogue import Dialogue
emotions = [
"(laughs)",
"(clears throat)",
"(sighs)",
"(gasps)",
"(coughs)",
"(singing)",
"(sings)",
"(mumbles)",
"(beep)",
"(groans)",
"(sniffs)",
"(claps)",
"(screams)",
"(inhales)",
"(exhales)",
"(applause)",
"(burps)",
"(humming)",
"(sneezes)",
"(chuckle)",
"(whistles)",
]
speakers = ["Speaker 1", "Speaker 2"]
client = httpx.AsyncClient(timeout=180)
async def query(dialogue: str, token: gr.OAuthToken | None):
if token is None:
raise gr.Error(
"No token provided. Use Sign in with Hugging Face to get a token."
)
API_URL = "https://router.huggingface.co/fal-ai/fal-ai/dia-tts"
headers = {
"Authorization": f"Bearer {token.token}",
}
response = await client.post(API_URL, headers=headers, json={"text": dialogue})
url = response.json()["audio"]["url"]
print("URL: ", url)
return url
def formatter(speaker, text):
speaker = speaker.split(" ")[1]
return f"[S{speaker}] {text}"
with gr.Blocks() as demo:
with gr.Sidebar():
login_button = gr.LoginButton()
gr.HTML(
"""
<h1 style='text-align: center; display: flex; align-items: center; justify-content: center;'>
<img src="/gradio_api/file=dancing_huggy.gif" alt="Dancing Huggy" style="height: 100px; margin-right: 10px"> Dia Dialogue Generation Model
</h1>
<h2 style='text-align: center; display: flex; align-items: center; justify-content: center;'>Model by <a href="https://huggingface.co./nari-labs/Dia-1.6B"> Nari Labs</a>. Powered by HF and <a href="https://fal.ai/">Fal AI</a> API.</h2>
<h3>Dia is a dialogue generation model that can generate realistic dialogue between two speakers. Use the dialogue component to create a conversation and then hit the submit button in the bottom right corner to see it come to life .</h3>
"""
)
with gr.Row():
with gr.Column():
dialogue = Dialogue(
speakers=speakers, emotions=emotions, formatter=formatter
)
with gr.Column():
with gr.Row():
audio = gr.Audio(label="Audio")
with gr.Row():
gr.DeepLinkButton(value="Share Audio via Link")
with gr.Row():
gr.Examples(
examples=[
[
[
{
"speaker": "Speaker 1",
"text": "Why did the chicken cross the road?",
},
{"speaker": "Speaker 2", "text": "I don't know!"},
{
"speaker": "Speaker 1",
"text": "to get to the other side! (laughs)",
},
]
],
[
[
{
"speaker": "Speaker 1",
"text": "I am a little tired today (sighs).",
},
{"speaker": "Speaker 2", "text": "Hang in there!"},
]
],
],
inputs=[dialogue],
cache_examples=False,
)
dialogue.submit(query, [dialogue], audio)
demo.launch(ssr_mode=False, allowed_paths=["dancing_huggy.gif"])
|