SAUL19 commited on
Commit
cb831b1
·
1 Parent(s): 04db253

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +12 -15
app.py CHANGED
@@ -76,7 +76,7 @@ def generateAudio(text_to_audio, s3_save_as, key_id):
76
  def save_text_to_speech(text, speaker=None):
77
  # Preprocess text and recortar
78
  text = cut_text(text, max_tokens=500)
79
-
80
  # Verificar si el texto tiene menos de 30 palabras
81
  palabras = text.split()
82
  if len(palabras) <= 30:
@@ -90,11 +90,20 @@ def generateAudio(text_to_audio, s3_save_as, key_id):
90
  speech = model.generate_speech(
91
  inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
92
  combined_audio = speech
 
 
 
 
 
 
 
 
 
93
  else:
94
  # Divide el texto en segmentos de 30 palabras
95
  segmentos = [' '.join(palabras[i:i+30])
96
  for i in range(0, len(palabras), 30)]
97
-
98
  # Generar audio para cada segmento y combinarlos
99
  audio_segments = []
100
  for segment in segmentos:
@@ -108,24 +117,12 @@ def generateAudio(text_to_audio, s3_save_as, key_id):
108
  speech = model.generate_speech(
109
  inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
110
  audio_segments.append(speech)
111
-
112
  if len(audio_segments) > 0:
113
  combined_audio = torch.cat(audio_segments, dim=0)
114
  else:
115
  combined_audio = None
116
 
117
- if combined_audio is not None:
118
- # Crear objeto BytesIO para almacenar el audio
119
- audio_buffer = BytesIO()
120
- sf.write(audio_buffer, combined_audio.cpu().numpy(),
121
- samplerate=16000, format='WAV')
122
- audio_buffer.seek(0)
123
-
124
- # Guardar el audio combinado en S3
125
- save_audio_to_s3(audio_buffer)
126
- else:
127
- print("File with content null")
128
-
129
  save_text_to_speech(text_to_audio, 2271)
130
  return s3_save_as
131
 
 
76
  def save_text_to_speech(text, speaker=None):
77
  # Preprocess text and recortar
78
  text = cut_text(text, max_tokens=500)
79
+
80
  # Verificar si el texto tiene menos de 30 palabras
81
  palabras = text.split()
82
  if len(palabras) <= 30:
 
90
  speech = model.generate_speech(
91
  inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
92
  combined_audio = speech
93
+
94
+ # Crear objeto BytesIO para almacenar el audio
95
+ audio_buffer = BytesIO()
96
+ sf.write(audio_buffer, combined_audio.cpu().numpy(),
97
+ samplerate=16000, format='WAV')
98
+ audio_buffer.seek(0)
99
+
100
+ # Guardar el audio combinado en S3
101
+ save_audio_to_s3(audio_buffer)
102
  else:
103
  # Divide el texto en segmentos de 30 palabras
104
  segmentos = [' '.join(palabras[i:i+30])
105
  for i in range(0, len(palabras), 30)]
106
+
107
  # Generar audio para cada segmento y combinarlos
108
  audio_segments = []
109
  for segment in segmentos:
 
117
  speech = model.generate_speech(
118
  inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
119
  audio_segments.append(speech)
120
+
121
  if len(audio_segments) > 0:
122
  combined_audio = torch.cat(audio_segments, dim=0)
123
  else:
124
  combined_audio = None
125
 
 
 
 
 
 
 
 
 
 
 
 
 
126
  save_text_to_speech(text_to_audio, 2271)
127
  return s3_save_as
128