app.py

from transformers import pipeline
import streamlit as st
import torch

device = "cuda:0" if torch.cuda.is_available() else "cpu"
pipe = pipeline('LLaVA', model='liuhaotian/llava-v1.5-13b', device=device )
text = st.text_area('Enter some text here!')

if text:
   out = pipe(text)
   st.json(out)


# from transformers import pipeline
# import torch

# device = "cuda:0" if torch.cuda.is_available() else "cpu"
# classifier = pipeline(
#     "audio-classification", model="MIT/ast-finetuned-speech-commands-v2", device=device
# )

# from transformers.pipelines.audio_utils import ffmpeg_microphone_live


# def launch_fn(
#     wake_word="marvin",
#     prob_threshold=0.5,
#     chunk_length_s=2.0,
#     stream_chunk_s=1,
#     debug=False,
# ):
#     if wake_word not in classifier.model.config.label2id.keys():
#         raise ValueError(
#             f"Wake word {wake_word} not in set of valid class labels, pick a wake word in the set {classifier.model.config.label2id.keys()}."
#         )

#     sampling_rate = classifier.feature_extractor.sampling_rate

#     mic = ffmpeg_microphone_live(
#         sampling_rate=sampling_rate,
#         chunk_length_s=chunk_length_s,
#         stream_chunk_s=stream_chunk_s,
#     )

#     print("Listening for wake word...")
#     mic_results = classifier(mic)
#     for prediction in mic_results:
#         prediction = prediction[0]
#         if debug:
#             print(prediction)
#         if prediction["label"] == wake_word:
#             if prediction["score"] > prob_threshold:
#                 return True

# launch_fn(debug=True)