Spaces:
Running
Running
File size: 2,320 Bytes
321fb0f ae68901 c370778 321fb0f 7c4c876 321fb0f c370778 c39573e 7c4c876 c39573e 7c4c876 c39573e 7c4c876 c39573e 321fb0f ae68901 321fb0f ae68901 321fb0f ae68901 |
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 |
import torch
import torchaudio
import streamlit as st
import requests
import streamlit.components.v1 as components
import asyncio
import io
import os
from dotenv import load_dotenv
load_dotenv()
model_id = '11mlabs/indri-0.1-124m-tts'
task = 'indri-tts'
st.title("Indri")
st.subheader("Ultrafast multi-modal AI")
baseUrl = os.getenv("BASE_URL")
speakers = {
"[spkr_63]" : "🇬🇧 👨 book reader",
"[spkr_67]" : "🇺🇸 👨 influencer",
"[spkr_68]" : "🇮🇳 👨 book reader",
"[spkr_69]" : "🇮🇳 👨 book reader",
"[spkr_70]" : "🇮🇳 👨 motivational speaker",
"[spkr_62]" : "🇮🇳 👨 book reader heavy",
"[spkr_53]" : "🇮🇳 👩 recipe reciter",
"[spkr_60]" : "🇮🇳 👩 book reader",
"[spkr_74]" : "🇺🇸 👨 book reader",
"[spkr_75]" : "🇮🇳 👨 entrepreneur",
"[spkr_76]" : "🇬🇧 👨 nature lover",
"[spkr_77]" : "🇮🇳 👨 influencer",
"[spkr_66]" : "🇮🇳 👨 politician"
}
with st.container():
st.markdown("### Speaker Selection")
speaker_id = st.selectbox("Select a speaker:", options=list(speakers.keys()), format_func=lambda x: speakers[x])
st.markdown("### Text Input")
text_input = st.text_area("Enter text for TTS (max 200 characters):", max_chars=200)
async def generate_audio():
if text_input:
speaker_name = speakers[speaker_id]
response = requests.post(
f"{baseUrl}/tts",
json={
"text": text_input,
"speaker": speaker_name
},
headers={
"accept": "application/json",
"Content-Type": "application/json"
}
)
if response.ok:
audio_blob = response.content
audio_tensor, sample_rate = torchaudio.load(io.BytesIO(audio_blob))
torchaudio.save('output.wav', audio_tensor, sample_rate=sample_rate)
st.audio('output.wav')
else:
st.warning(f"Received invalid response format. Status Code: {response.status_code}, Response: {response.text}")
else:
st.warning("Please enter text to generate audio.")
if st.button("Generate Audio", key="generate_audio"):
asyncio.run(generate_audio())
|