Spaces:
Sleeping
Sleeping
gggg
Browse files
app.py
CHANGED
@@ -10,24 +10,26 @@ from transformers import MarianMTModel, MarianTokenizer
|
|
10 |
|
11 |
|
12 |
# Cargar el modelo Whisper-small y bark
|
13 |
-
|
14 |
"""bark = pipeline("text-to-speech", model="suno/bark")"""
|
15 |
|
16 |
|
17 |
# Cargar el tokenizador y el modelo para espa帽ol a ingl茅s
|
18 |
-
|
19 |
-
tokenizer = MarianTokenizer.from_pretrained(model_name)
|
20 |
-
model = MarianMTModel.from_pretrained(model_name)
|
21 |
|
22 |
|
23 |
# Funci贸n para transcribir el audio y traducir el audio de entrada
|
24 |
def transcribir_audio(audio):
|
25 |
# Usamos el pipeline de Hugging Face para la transcripci贸n
|
26 |
-
|
|
|
27 |
return result["text"]
|
28 |
|
29 |
|
30 |
def traducir_texto(texto):
|
|
|
|
|
|
|
31 |
# Tokenizar el texto
|
32 |
inputs = tokenizer(texto, return_tensors="pt", padding=True, truncation=True)
|
33 |
# Generar la traducci贸n
|
@@ -46,9 +48,20 @@ def generar_audio(text):
|
|
46 |
temp_wav = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
|
47 |
write(temp_wav.name, 24000, (audio_array * 32767).astype(np.int16))
|
48 |
return temp_wav.name
|
49 |
-
|
50 |
|
51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
def process_audio(audio_file):
|
53 |
try:
|
54 |
# Paso 1: Transcripci贸n con Whisper
|
|
|
10 |
|
11 |
|
12 |
# Cargar el modelo Whisper-small y bark
|
13 |
+
|
14 |
"""bark = pipeline("text-to-speech", model="suno/bark")"""
|
15 |
|
16 |
|
17 |
# Cargar el tokenizador y el modelo para espa帽ol a ingl茅s
|
18 |
+
|
|
|
|
|
19 |
|
20 |
|
21 |
# Funci贸n para transcribir el audio y traducir el audio de entrada
|
22 |
def transcribir_audio(audio):
|
23 |
# Usamos el pipeline de Hugging Face para la transcripci贸n
|
24 |
+
transcribir = pipeline("automatic-speech-recognition", model="openai/whisper-small")
|
25 |
+
result = transcribir(audio)
|
26 |
return result["text"]
|
27 |
|
28 |
|
29 |
def traducir_texto(texto):
|
30 |
+
model_name = "Helsinki-NLP/opus-mt-es-en"
|
31 |
+
tokenizer = MarianTokenizer.from_pretrained(model_name)
|
32 |
+
model = MarianMTModel.from_pretrained(model_name)
|
33 |
# Tokenizar el texto
|
34 |
inputs = tokenizer(texto, return_tensors="pt", padding=True, truncation=True)
|
35 |
# Generar la traducci贸n
|
|
|
48 |
temp_wav = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
|
49 |
write(temp_wav.name, 24000, (audio_array * 32767).astype(np.int16))
|
50 |
return temp_wav.name
|
|
|
51 |
|
52 |
|
53 |
+
"""def process_audio(audio_file):
|
54 |
+
try:
|
55 |
+
# Paso 1: Transcripci贸n y traducci贸n con Whisper
|
56 |
+
transcripcion_traducida = transcribir_audio(audio_file)
|
57 |
+
|
58 |
+
# Paso 2: Generaci贸n de audio con Bark
|
59 |
+
audio_sintetizado = generar_audio(transcripcion_traducida)
|
60 |
+
|
61 |
+
return transcripcion_traducida, audio_sintetizado
|
62 |
+
except Exception as e:
|
63 |
+
return str(e), None"""
|
64 |
+
|
65 |
def process_audio(audio_file):
|
66 |
try:
|
67 |
# Paso 1: Transcripci贸n con Whisper
|