Spaces:
Sleeping
Sleeping
unilight
commited on
Commit
·
d2ddbfd
1
Parent(s):
48ce4d1
change input type
Browse files
app.py
CHANGED
@@ -128,8 +128,13 @@ def predict(model_name, wav_file):
|
|
128 |
with gr.Blocks(title="S3PRL-VC: Any-to-one voice conversion demo on VCC2020") as demo:
|
129 |
gr.Markdown(
|
130 |
"""
|
131 |
-
#
|
132 |
-
### [
|
|
|
|
|
|
|
|
|
|
|
133 |
**S3PRL-VC** is a voice conversion (VC) toolkit for benchmarking self-supervised speech representations (S3Rs). The term **any-to-one** means that the system can convert from any unseen speaker to a pre-defined speaker given in training.
|
134 |
In this demo, you can record your voice, and the model will convert your voice to one of the four pre-defined speakers. These four speakers come from the **voice conversion challenge (VCC) 2020**. You can listen to the samples to get a sense of what these speakers sound like.
|
135 |
The **RTF** of the system is around **1.5~2.5**, i.e. if you recorded a 5 second long audio, it will take 5 * (1.5~2.5) = 7.5~12.5 seconds to generate the output.
|
@@ -139,7 +144,7 @@ with gr.Blocks(title="S3PRL-VC: Any-to-one voice conversion demo on VCC2020") as
|
|
139 |
with gr.Row():
|
140 |
with gr.Column():
|
141 |
gr.Markdown("## Record your speech here!")
|
142 |
-
input_wav = gr.Audio(label="Input speech",
|
143 |
|
144 |
gr.Markdown("## Select a model!")
|
145 |
model_name = gr.Radio(label="Model", choices=list(model_paths.keys()))
|
|
|
128 |
with gr.Blocks(title="S3PRL-VC: Any-to-one voice conversion demo on VCC2020") as demo:
|
129 |
gr.Markdown(
|
130 |
"""
|
131 |
+
# Demo for SHEET: Speech Human Evaluation Estimation Toolkit
|
132 |
+
### [Paper (To be uploaded)] [[Code]](https://github.com/unilight/sheet)
|
133 |
+
**SHEET** is a subjective speech quality assessment (SSQA) toolkit designed to conduct SSQA research. It was specifically designed to interactive with MOS-Bench, a collective of datasets to benchmark SSQA models.
|
134 |
+
|
135 |
+
|
136 |
+
In this demo, we provide interactive models
|
137 |
+
|
138 |
**S3PRL-VC** is a voice conversion (VC) toolkit for benchmarking self-supervised speech representations (S3Rs). The term **any-to-one** means that the system can convert from any unseen speaker to a pre-defined speaker given in training.
|
139 |
In this demo, you can record your voice, and the model will convert your voice to one of the four pre-defined speakers. These four speakers come from the **voice conversion challenge (VCC) 2020**. You can listen to the samples to get a sense of what these speakers sound like.
|
140 |
The **RTF** of the system is around **1.5~2.5**, i.e. if you recorded a 5 second long audio, it will take 5 * (1.5~2.5) = 7.5~12.5 seconds to generate the output.
|
|
|
144 |
with gr.Row():
|
145 |
with gr.Column():
|
146 |
gr.Markdown("## Record your speech here!")
|
147 |
+
input_wav = gr.Audio(label="Input speech", type='filepath')
|
148 |
|
149 |
gr.Markdown("## Select a model!")
|
150 |
model_name = gr.Radio(label="Model", choices=list(model_paths.keys()))
|