Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -40,20 +40,23 @@ def extract_zip_file(zip_file: str) -> bool:
|
|
40 |
print(f"Error extracting zip file: {e}")
|
41 |
return False
|
42 |
|
43 |
-
def
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
return input_audio_file
|
52 |
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
|
|
|
|
|
|
|
|
57 |
|
58 |
def voice_clone(text: str, input_file: gr.File, language: str, url: gr.Audio) -> str:
|
59 |
if input_file is not None:
|
@@ -72,7 +75,7 @@ def voice_clone(text: str, input_file: gr.File, language: str, url: gr.Audio) ->
|
|
72 |
return"Error: Please select a file or enter a URL"
|
73 |
if language not in LANGUAGES:
|
74 |
return "Error: Invalid language selected"
|
75 |
-
output_file_path = synthesize_text(text, input_audio_file,
|
76 |
return output_file_path
|
77 |
|
78 |
iface = gr.Interface(
|
|
|
40 |
print(f"Error extracting zip file: {e}")
|
41 |
return False
|
42 |
|
43 |
+
def convert_to_wav(input_audio_file: str) -> str:
|
44 |
+
file_extension = os.path.splitext(input_audio_file)[-1].lower()
|
45 |
+
if file_extension!= ".wav":
|
46 |
+
audio = AudioSegment.from_file(input_audio_file)
|
47 |
+
audio.export("temp.wav", format="wav")
|
48 |
+
os.remove(input_audio_file)
|
49 |
+
return "temp.wav"
|
50 |
+
return input_audio_file
|
|
|
51 |
|
52 |
+
def synthesize_text(text: str, input_audio_file: str, language: str) -> str:
|
53 |
+
input_audio_file = convert_to_wav(input_audio_file)
|
54 |
+
tts.tts_to_file(text=text, speaker_wav=input_audio_file, language=language, file_path="./output.wav")
|
55 |
+
return "./output.wav"
|
56 |
+
|
57 |
+
@audio_processing
|
58 |
+
def process_audio(input_audio_file: str) -> str:
|
59 |
+
return input_audio_file
|
60 |
|
61 |
def voice_clone(text: str, input_file: gr.File, language: str, url: gr.Audio) -> str:
|
62 |
if input_file is not None:
|
|
|
75 |
return"Error: Please select a file or enter a URL"
|
76 |
if language not in LANGUAGES:
|
77 |
return "Error: Invalid language selected"
|
78 |
+
output_file_path = synthesize_text(text, input_audio_file,language)
|
79 |
return output_file_path
|
80 |
|
81 |
iface = gr.Interface(
|