Spaces:
Running
on
Zero
Running
on
Zero
added mic input
Browse files
README.md
CHANGED
@@ -10,7 +10,7 @@ pinned: false
|
|
10 |
license: mit
|
11 |
---
|
12 |
# CocoCap-beta
|
13 |
-
このスペースでは,[CocoNutコーパス](https://sites.google.com/site/shinnosuketakamichi/research-topics/coconut_corpus)でfinetuningした[OpenAI whisper](https://github.com/openai/whisper)
|
14 |
|
15 |
# Contributors / 貢献者
|
16 |
* [中田 亘](https://wataru-nakata.github.io)
|
|
|
10 |
license: mit
|
11 |
---
|
12 |
# CocoCap-beta
|
13 |
+
このスペースでは,[CocoNutコーパス](https://sites.google.com/site/shinnosuketakamichi/research-topics/coconut_corpus)でfinetuningした[OpenAI whisper](https://github.com/openai/whisper)による声質キャプショニング(どんな人がどんなスタイルで喋っているかの文章化)を示します.
|
14 |
|
15 |
# Contributors / 貢献者
|
16 |
* [中田 亘](https://wataru-nakata.github.io)
|
app.py
CHANGED
@@ -14,10 +14,15 @@ def main(audio_path):
|
|
14 |
return transcribe(audio_path)["text"]
|
15 |
|
16 |
|
|
|
|
|
|
|
|
|
17 |
|
18 |
iface = gr.Interface(
|
19 |
fn=main,
|
20 |
-
inputs=gr.
|
|
|
21 |
outputs="text",
|
22 |
-
title="
|
23 |
).launch(share=True)
|
|
|
14 |
return transcribe(audio_path)["text"]
|
15 |
|
16 |
|
17 |
+
with open('./README.md') as f:
|
18 |
+
md = f.readlines()
|
19 |
+
md = md[11:]
|
20 |
+
md = "\n".join(md)
|
21 |
|
22 |
iface = gr.Interface(
|
23 |
fn=main,
|
24 |
+
inputs=[gr.Audio(type='filepath',sources=['microphone','upload'])],
|
25 |
+
description=md,
|
26 |
outputs="text",
|
27 |
+
title="CoCoCap-beta 日本語声質キャプショニンング with CocoNut Corpus",
|
28 |
).launch(share=True)
|