Spaces:
Runtime error
Runtime error
Ahsen Khaliq
commited on
Commit
•
ebe1109
1
Parent(s):
6f53eb2
Update app.py
Browse files
app.py
CHANGED
@@ -79,7 +79,7 @@ def inference(text,lang):
|
|
79 |
scipy.io.wavfile.write("out.wav",text2speechen.fs , wav.view(-1).cpu().numpy())
|
80 |
if lang == "chinese":
|
81 |
wav = text2speechch(text)["wav"]
|
82 |
-
scipy.io.wavfile.write("out.wav",
|
83 |
if lang == "japanese":
|
84 |
wav = text2speechjp(text)["wav"]
|
85 |
scipy.io.wavfile.write("out.wav",text2speechjp.fs , wav.view(-1).cpu().numpy())
|
@@ -88,7 +88,7 @@ title = "ESPnet2-TTS"
|
|
88 |
description = "Gradio demo for ESPnet2-TTS: Extending the Edge of TTS Research. To use it, simply add your audio, or click one of the examples to load them. Read more at the links below."
|
89 |
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2110.07840' target='_blank'>ESPnet2-TTS: Extending the Edge of TTS Research</a> | <a href='https://github.com/espnet/espnet' target='_blank'>Github Repo</a></p>"
|
90 |
|
91 |
-
examples=[['This paper describes ESPnet2-TTS, an end-to-end text-to-speech (E2E-TTS) toolkit. ESPnet2-TTS extends our earlier version, ESPnet-TTS, by adding many new features, including: on-the-fly flexible pre-processing, joint training with neural vocoders, and state-of-the-art TTS models with extensions like full-band E2E text-to-waveform modeling, which simplify the training pipeline and further enhance TTS performance. The unified design of our recipes enables users to quickly reproduce state-of-the-art E2E-TTS results',"english"],['水をマレーシアから買わなくてはならないのです。',"japanese"],['
|
92 |
|
93 |
gr.Interface(
|
94 |
inference,
|
|
|
79 |
scipy.io.wavfile.write("out.wav",text2speechen.fs , wav.view(-1).cpu().numpy())
|
80 |
if lang == "chinese":
|
81 |
wav = text2speechch(text)["wav"]
|
82 |
+
scipy.io.wavfile.write("out.wav",text2speechch.fs , wav.view(-1).cpu().numpy())
|
83 |
if lang == "japanese":
|
84 |
wav = text2speechjp(text)["wav"]
|
85 |
scipy.io.wavfile.write("out.wav",text2speechjp.fs , wav.view(-1).cpu().numpy())
|
|
|
88 |
description = "Gradio demo for ESPnet2-TTS: Extending the Edge of TTS Research. To use it, simply add your audio, or click one of the examples to load them. Read more at the links below."
|
89 |
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2110.07840' target='_blank'>ESPnet2-TTS: Extending the Edge of TTS Research</a> | <a href='https://github.com/espnet/espnet' target='_blank'>Github Repo</a></p>"
|
90 |
|
91 |
+
examples=[['This paper describes ESPnet2-TTS, an end-to-end text-to-speech (E2E-TTS) toolkit. ESPnet2-TTS extends our earlier version, ESPnet-TTS, by adding many new features, including: on-the-fly flexible pre-processing, joint training with neural vocoders, and state-of-the-art TTS models with extensions like full-band E2E text-to-waveform modeling, which simplify the training pipeline and further enhance TTS performance. The unified design of our recipes enables users to quickly reproduce state-of-the-art E2E-TTS results',"english"],['水をマレーシアから買わなくてはならないのです。',"japanese"],['对英语和日语语料库的实验评估表明,我们提供的模型合成了与真实情况相当的话语,达到了最先进的水平',"chinese"]]
|
92 |
|
93 |
gr.Interface(
|
94 |
inference,
|