app2.py

import torch
# from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from transformers import pipeline, WhisperProcessor, WhisperForConditionalGeneration
import gradio as gr
import datetime

"""
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "distil-whisper/distil-small.en"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, use_safetensors=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    max_new_tokens=128,
    torch_dtype=torch_dtype,
    device=device,
)
"""
# call a text generation model to display the audio content after identifying the word(s) in the text output

# import torch
# from transformers import pipeline
# from datasets import load_dataset


# from transformers import WhisperProcessor, WhisperForConditionalGeneration
# from datasets import load_dataset

# load model and processor
processor = WhisperProcessor.from_pretrained("microsoft/whisper-base-webnn")
model = WhisperForConditionalGeneration.from_pretrained("microsoft/whisper-base-webnn")
model.config.forced_decoder_ids = None

# load dummy dataset and read audio files
# ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
# sample = ds[0]["audio"]

"""
device = "cuda:0" if torch.cuda.is_available() else "cpu"

pipe = pipeline(
    "automatic-speech-recognition",
  # model="openai/whisper-base",
    model = "microsoft/whisper-base-webnn",
    chunk_length_s=30,
    device=device,
)
"""
# ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
# sample = ds[0]["audio"]

# prediction = pipe(sample.copy(), batch_size=8)["text"]

# we can also return timestamps for the predictions
#prediction = pipe(sample.copy(), batch_size=8, return_timestamps=True)["chunks"]


def audio2text(audio_file, prompt : list):
    
    input_features = processor(audio_file, sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features 

    # generate token ids
    predicted_ids = model.generate(input_features)
    # decode token ids to text
    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
    
    # transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)

    # prediction = pipe(audio_file, batch_size=8, return_timestamps=True)["chunks"]
    #prediction=pipe(audio_file)
    return transcription['text']

gr.Interface(fn=audio2text, inputs=[gr.Audio(label='upload your audio file', sources='upload', type='filepath'), gr.Textbox(label="provide word(s) to search for")], outputs=[gr.Textbox(label="transcription")]).launch()