adding translation

app.py

@@ -1,33 +1,22 @@
-from transformers import pipeline
 import gradio as gr
+import whisper
+import numpy as np
 import pytube as pt
-import torch
 
-MODEL_NAME = "openai/whisper-medium"
-device = 0 if torch.cuda.is_available() else "cpu"
-
-transcriptor = pipeline(
-    task="automatic-speech-recognition",
-    model=MODEL_NAME,
-    chunk_length_s=30,
-    device=device,
+model = whisper.load_model("medium")
+print(
+    f"Model is {'multilingual' if model.is_multilingual else 'English-only'} "
+    f"and has {sum(np.prod(p.shape) for p in model.parameters()):,} parameters."
 )
-# transcriptor.model.config.forced_decoder_ids = transcriptor.tokenizer.get_decoder_prompt_ids(language='en',
-#                                                                                              task="transcribe")
 
-translator = pipeline(
-    task="automatic-speech-recognition",
-    model=MODEL_NAME,
-    chunk_length_s=30,
-    device=device,
-)
-# translator.model.config.forced_decoder_ids = translator.tokenizer.get_decoder_prompt_ids(language='es',
-#                                                                                          task="translate")
+options = dict(language='es', beam_size=5, best_of=5)
+transcribe_options = dict(task="transcribe", **options)
+translate_options = dict(task="translate", **options)
 
 
 def transcribe(audio):
-    transcription = transcriptor(audio)
-    translation = translator(audio)
+    transcription = model.transcribe(audio, **transcribe_options)
+    translation = model.transcribe(audio, **translate_options)
     return transcription["text"], translation["text"]
 
 
@@ -63,7 +52,7 @@ youtube_interface = gr.Interface(
     fn=youtube_transcribe,
     inputs="text",
     outputs=["text", "text"],
-    title="Transcribir y traducir video de YouTube",
+    title="Transcribir y traducir audio",
 )
 
 if __name__ == "__main__":

requirements.txt

@@ -1,6 +1,74 @@
-transformers
-tensorflow
-torch
-sentencepiece
-numpy
-pytube
+aiohttp==3.8.3
+aiosignal==1.3.1
+anyio==3.6.2
+async-timeout==4.0.2
+attrs==22.1.0
+bcrypt==4.0.1
+certifi==2022.9.24
+cffi==1.15.1
+charset-normalizer==2.1.1
+click==8.1.3
+contourpy==1.0.6
+cryptography==38.0.4
+cycler==0.11.0
+fastapi==0.88.0
+ffmpeg-python==0.2.0
+ffmpy==0.3.0
+filelock==3.8.2
+fonttools==4.38.0
+frozenlist==1.3.3
+fsspec==2022.11.0
+future==0.18.2
+gradio==3.12.0
+h11==0.12.0
+httpcore==0.15.0
+httpx==0.23.1
+huggingface-hub==0.11.1
+idna==3.4
+Jinja2==3.1.2
+kiwisolver==1.4.4
+linkify-it-py==1.0.3
+markdown-it-py==2.1.0
+MarkupSafe==2.1.1
+matplotlib==3.6.2
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+more-itertools==9.0.0
+multidict==6.0.3
+numpy==1.23.5
+orjson==3.8.3
+packaging==21.3
+pandas==1.5.2
+paramiko==2.12.0
+Pillow==9.3.0
+pycparser==2.21
+pycryptodome==3.16.0
+pydantic==1.10.2
+pydub==0.25.1
+PyNaCl==1.5.0
+pyparsing==3.0.9
+python-dateutil==2.8.2
+python-multipart==0.0.5
+pytz==2022.6
+PyYAML==6.0
+regex==2022.10.31
+requests==2.28.1
+rfc3986==1.5.0
+semantic-version==2.10.0
+setuptools-rust==1.5.2
+six==1.16.0
+sniffio==1.3.0
+starlette==0.22.0
+tokenizers==0.13.2
+torch==1.13.0
+tqdm==4.64.1
+transformers==4.25.1
+typing_extensions==4.4.0
+uc-micro-py==1.0.1
+urllib3==1.26.13
+uvicorn==0.20.0
+websockets==10.4
+whisper @ git+https://github.com/openai/whisper.git@fd8f80c8b880dd7c284c109ca7f03dbe978bc532
+yarl==1.8.2
+
+pytube~=12.1.0