|
|
import spaces |
|
|
import tempfile |
|
|
import wave |
|
|
import gradio as gr |
|
|
import os |
|
|
from whisperspeech.pipeline import Pipeline |
|
|
import torch |
|
|
import soundfile as sf |
|
|
import numpy as np |
|
|
import torch.nn.functional as F |
|
|
from whisperspeech.languages import LANGUAGES |
|
|
from whisperspeech.pipeline import Pipeline |
|
|
from whisperspeech.utils import resampler |
|
|
|
|
|
title = """# 🙋🏻♂️ Welcome to🌟Tonic's🌬️💬📝WhisperSpeech |
|
|
|
|
|
You can use this ZeroGPU Space to test out the current model [🌬️💬📝collabora/whisperspeech](https://huggingface.co/collabora/whisperspeech). 🌬️💬📝collabora/whisperspeech is An Open Source text-to-speech system built by inverting Whisper. Previously known as spear-tts-pytorch. It's like Stable Diffusion but for speech – both powerful and easily customizable. |
|
|
You can also use 🌬️💬📝WhisperSpeech by cloning this space. 🧬🔬🔍 Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/Tonic/laion-whisper?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3> |
|
|
Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's🛠️community 👻 [](https://discord.gg/GWpVpekp) On 🤗Huggingface: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Polytonic](https://github.com/tonic-ai) & contribute to 🌟 [Poly](https://github.com/tonic-ai/poly) 🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗 |
|
|
""" |
|
|
|
|
|
@spaces.GPU |
|
|
def whisper_speech_demo(text, lang, speaker_audio, mix_lang, mix_text): |
|
|
print(f"Text: {text}, Lang: {lang}, Speaker Audio: {speaker_audio}, Mix Lang: {mix_lang}, Mix Text: {mix_text}") |
|
|
pipe = Pipeline() |
|
|
speaker_url = speaker_audio if speaker_audio is not None else None |
|
|
if isinstance(lang, list): |
|
|
if not lang: |
|
|
raise ValueError("Language list is empty.") |
|
|
lang = lang[0] |
|
|
elif not isinstance(lang, str): |
|
|
raise ValueError("Language is not specified correctly.") |
|
|
|
|
|
if mix_lang and mix_text: |
|
|
mixed_langs = mix_lang.split(',') if isinstance(mix_lang, str) else mix_lang |
|
|
mixed_texts = mix_text.split(',') |
|
|
stoks = pipe.t2s.generate(mixed_texts, lang=mixed_langs) |
|
|
audio_data = pipe.generate(stoks, speaker_url, lang=mixed_langs[0]) |
|
|
else: |
|
|
audio_data = pipe.generate(text, speaker_url, lang) |
|
|
|
|
|
resample_audio = resampler(newsr=24000) |
|
|
audio_data_resampled = next(resample_audio([{'sample_rate': 24000, 'samples': audio_data.cpu()}]))['samples_24k'] |
|
|
audio_np = audio_data_resampled.cpu().numpy() |
|
|
audio_np = audio_np / np.max(np.abs(audio_np)) |
|
|
audio_np = np.asarray(audio_np, dtype=np.float32) |
|
|
|
|
|
audio_stereo = np.stack((audio_np, audio_np), axis=-1) |
|
|
audio_stereo = audio_stereo.reshape(-1, 2) |
|
|
|
|
|
print("Audio Array Shape:", audio_stereo.shape) |
|
|
print("Audio Array Dtype:", audio_stereo.dtype) |
|
|
with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as tmp_file: |
|
|
sf.write(tmp_file.name, audio_stereo, 24000, format='WAV', subtype='PCM_16') |
|
|
return tmp_file.name |
|
|
|
|
|
with gr.Blocks() as demo: |
|
|
gr.Markdown(title) |
|
|
|
|
|
with gr.Tabs(): |
|
|
with gr.TabItem("🌬️💬📝Standard TTS"): |
|
|
with gr.Row(): |
|
|
text_input_standard = gr.Textbox(label="Enter text") |
|
|
lang_input_standard = gr.Dropdown(choices=list(LANGUAGES.keys()), label="Language") |
|
|
speaker_input_standard = gr.Audio(label="Upload or Record Speaker Audio (optional)", sources=["upload", "microphone"], type="filepath") |
|
|
placeholder_mix_lang = gr.Textbox(visible=False) |
|
|
placeholder_mix_text = gr.Textbox(visible=False) |
|
|
generate_button_standard = gr.Button("Generate Speech") |
|
|
output_audio_standard = gr.Audio(label="🌬️💬📝WhisperSpeech") |
|
|
|
|
|
generate_button_standard.click( |
|
|
whisper_speech_demo, |
|
|
inputs=[text_input_standard, lang_input_standard, speaker_input_standard, placeholder_mix_lang, placeholder_mix_text], |
|
|
outputs=output_audio_standard |
|
|
) |
|
|
|
|
|
with gr.TabItem("🌬️💬📝Mixed Language TTS"): |
|
|
with gr.Row(): |
|
|
placeholder_text_input = gr.Textbox(visible=False) |
|
|
placeholder_lang_input = gr.Dropdown(choices=[], visible=False) |
|
|
placeholder_speaker_input = gr.Audio(visible=False) |
|
|
mix_lang_input_mixed = gr.CheckboxGroup(choices=list(LANGUAGES.keys()), label="Select Languages") |
|
|
mix_text_input_mixed = gr.Textbox(label="Enter mixed language text", placeholder="e.g., Hello, Cześć") |
|
|
generate_button_mixed = gr.Button("Generate Mixed Speech") |
|
|
output_audio_mixed = gr.Audio(label="Mixed🌬️💬📝WhisperSpeech") |
|
|
|
|
|
generate_button_mixed.click( |
|
|
whisper_speech_demo, |
|
|
inputs=[placeholder_text_input, placeholder_lang_input, placeholder_speaker_input, mix_lang_input_mixed, mix_text_input_mixed], |
|
|
outputs=output_audio_mixed |
|
|
) |
|
|
|
|
|
demo.launch() |
