app.py

import streamlit as st
import whisper
from transformers import pipeline
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
SAMPLE_RATE = 16000

def load_audio(file: str, sr: int = SAMPLE_RATE):

    try:
        # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
        # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
        out, _ = (
            ffmpeg.input(file, threads=0)
            .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=sr)
            .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
        )
    except ffmpeg.Error as e:
        raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e

    return np.frombuffer(out, np.int16).flatten().astype(np.float32) / 32768.0
if 'processor' not in locals():
 processor = AutoProcessor.from_pretrained("openai/whisper-tiny")
 model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-tiny")



pipe = pipeline('sentiment-analysis')
#pipe2 =  pipeline(task="image-bestify", model="beihai/GFPGAN-V1.3-whole-image")
text = st.text_area('entre com algum texto')
st.title("Hot Dog? Or Not? ")

file_name = st.file_uploader("Upload a hot dog candidate image")
print(file_name)
if file_name:
 audio = load_audio(file_name )
 print('2')
 input_features = processor(audio , return_tensors="pt").input_features 
 forced_decoder_ids = processor.get_decoder_prompt_ids(language = "pt", task = "translate")

 predicted_ids = model.generate(input_features, forced_decoder_ids = forced_decoder_ids)
 transcription = processor.batch_decode(predicted_ids, skip_special_tokens = True)
 st.title(transcription )
print('3')
if text:
 out=pipe(text)
 st.json(out)