karimouda's picture
Upload app.py
9fa8261 verified
import csv
import gradio as gr
import os
import time
import os
import pandas as pd
app = None
os.environ['GRADIO_ANALYTICS_ENABLED'] = 'False'
CURR_BASE_DIR = os.getcwd()
BASE_AUDIOS_DIR = os.path.join(os.getcwd(), "results")
BASE_VIDEO_DIR = BASE_AUDIOS_DIR
should_stop = False
current_process = None
if not os.path.exists(BASE_AUDIOS_DIR):
os.makedirs(BASE_AUDIOS_DIR)
custom_css = """
.gradio-container{
background-color: unset;
}
input, textarea {
font-family: 'Noto Naskh Arabic', 'Arial', sans-serif !important;
}
.large_text input{
font-size:20px !important
}
.tab-container button{
font-weight: bold !important;
}
.tabs{
gap:0px !important;
}
.tabitem{
padding:0px !important;
}
button.secondary:hover{
background-color:steelblue !important;
color:white;
}
.tab-container button {
font-size:20px !important;
}
.tabitem{
padding-top:0px !important;
}
#tool-header{
padding:20px 0px 20px 0px !important;
}
#tool-header h1{
display: flex;
align-items: center;
}
#tool-header img{
width: 80px;
display: inline-block;
margin-right: 10px;
border-radius: 5px;
}
"""
def natural_sort_key(file_name):
if ".DS_Store" in file_name:
return 0
return int(file_name.split("_")[1])
def get_data(folders_list, language="msa"):
results_csv_df = pd.read_csv(f"{CURR_BASE_DIR}/results/{language}/Ar_{language}_TTS_benchmark.csv")
data_map = {}
try:
for folder_name in folders_list:
full_audio_folder_path = os.path.join(BASE_AUDIOS_DIR,language ,folder_name)
if not os.path.exists(full_audio_folder_path):
print(f"Folder not found: {full_audio_folder_path}")
continue
if folder_name not in data_map:
data_map[folder_name] = []
##get all wavs and mp3s from full_audio_folder_path
for file in sorted(os.listdir(full_audio_folder_path), key=natural_sort_key):
if ".DS_Store" in file:
continue
if file.endswith(".wav") or file.endswith(".mp3"):
abs_path = os.path.join(full_audio_folder_path, file)
data_map[folder_name].append(abs_path)
final_df = pd.DataFrame(columns=["Text"].extend(folders_list))
final_df["Text"] = results_csv_df["Text"]
cache_random_hash = str(time.time())
for folder_name in data_map:
folder_files_list = data_map[folder_name]
formatted_column = pd.Series(folder_files_list).apply(
lambda file_path: f'<audio controls src="/gradio_api/file={file_path}?h={cache_random_hash}" type="audio/mpeg" style="width: 100%;"></audio>'
)
## append column to dataframe
final_df[folder_name] = formatted_column
return final_df
except Exception as e:
print(f"An error occurred: {e}")
gr.Warning(f"An error occurred: {e}")
raise e
with gr.Blocks(css=custom_css) as app:
gr.HTML(
f"""<h1><img src='/gradio_api/file={CURR_BASE_DIR}/images/silma-logo.png'/>Open-source Arabic TTS Benchmark</h1>
<br>
<p style="font-size:16px">
This benchmark represents a foundational step by <a href="https://silma.ai">SILMA.AI</a> towards establishing a high-quality benchmark for open-source Arabic TTS models. We have found that standard quantitative metrics (such as WER, CER, SIM, and UTMOS) are often insufficient for accurately capturing the nuances of Arabic speech. Consequently, for this release we have prioritized direct auditory assessment, allowing listeners to evaluate the naturalness and quality of the models themselves. More advanced releases will follow as we develop the necessary technology.
You can also check our <a href="https://huggingface.co/spaces/silma-ai/arabic-tts-benchmark" target="blank">Commercial Arabic TTS Benchmark</a>
</p>
<p>
Note: To make the benchmark more manageable, we have excluded models that require Tashkeel, as well as those based on old architectures
</p
""",
elem_id="tool-header"
)
with gr.Tabs():
with gr.TabItem("Modern Standard Arabic (MSA)"):
folders_list = ["habibi_specialized","xtts"]
df_header = ["Text","Habibi MSA Specialized","Coqui (XTTS)"]
data_df = get_data(folders_list, language="msa")
data_df.columns = df_header
data_viewer = gr.Dataframe(
datatype=["html"]+(["html"] * len(folders_list)),
value=data_df,
column_widths=[200]+([200]*len(folders_list)),
wrap=True,
show_label=True,
show_row_numbers=True,
interactive=True,
elem_classes="data_viewer_dataframe",
show_search="search",
visible=True,
)
with gr.TabItem("EGY"):
folders_list = ["habibi","egtts","chatterbox_masri"]
df_header = ["Text","Habibi EGY Specialized","EGTTS V0.1","Chatterbox-Egyptian"]
data_df = get_data(folders_list, language="egy")
data_df.columns = df_header
data_viewer = gr.Dataframe(
datatype=["html"]+(["html"] * len(folders_list)),
value=data_df,
column_widths=[200,200,200,200,200],
wrap=True,
show_label=True,
show_row_numbers=True,
interactive=True,
elem_classes="data_viewer_dataframe",
show_search="search",
visible=True
)
with gr.TabItem("KSA"):
folders_list = ["habibi"]
df_header = ["Text","Habibi KSA Specialized"]
data_df = get_data(folders_list, language="ksa")
data_df.columns = df_header
data_viewer = gr.Dataframe(
datatype=["html"]+(["html"] * len(folders_list)),
value=data_df,
column_widths=[200,200,200,200,200],
wrap=True,
show_label=True,
show_row_numbers=True,
interactive=True,
elem_classes="data_viewer_dataframe",
show_search="search",
visible=True
)
with gr.TabItem("UAE"):
folders_list = ["habibi"]
df_header = ["Text","Habibi UAE Specialized"]
data_df = get_data(folders_list, language="uae")
data_df.columns = df_header
data_viewer = gr.Dataframe(
datatype=["html"]+(["html"] * len(folders_list)),
value=data_df,
column_widths=[200,200,200,200,200],
wrap=True,
show_label=True,
show_row_numbers=True,
interactive=True,
elem_classes="data_viewer_dataframe",
show_search="search",
visible=True
)
with gr.Row():
## add link for each model
with gr.Column():
gr.Markdown("Benchmark model links:")
gr.Markdown("""
- <a href="https://huggingface.co/SWivid/Habibi-TTS" target="_blank">Habibi-TTS</a>
- <a href="https://huggingface.co/coqui/XTTS-v2" target="_blank">XTTS-v2</a>
- <a href="https://huggingface.co/OmarSamir/EGTTS-V0.1" target="_blank">EGTTS-v0.1</a>
- <a href="https://huggingface.co/oddadmix/chatterbox-egyptian-v0" target="_blank">Chatterbox-Egyptian</a>
""")
with gr.Column():
gr.Markdown("Other models:")
gr.Markdown("""
- <a href="https://huggingface.co/IbrahimSalah/Arabic-F5-TTS-v2" target="_blank">Arabic-F5-TTS-v2</a>
- <a href="https://huggingface.co/IbrahimSalah/Arabic-TTS-Spark" target="_blank">Arabic-TTS-Spark</a>
- <a href="https://huggingface.co/MrEzzat/Spark_TTS_Arabic" target="_blank">Spark_TTS_Arabic</a>
""")
def main():
global app
print("Starting app...")
app.queue().launch(favicon_path="images/silma-favicon.png", allowed_paths=[CURR_BASE_DIR+"/images/",CURR_BASE_DIR+"/results/"])
if __name__ == "__main__":
main()