File size: 1,463 Bytes
1c3348e d1dfef4 fcc37fb d1dfef4 1c3348e d1dfef4 1c3348e d1dfef4 1c3348e d1dfef4 1c3348e 2432ca4 460d74e 2432ca4 1c3348e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
import gradio as gr
from transformers import WhisperProcessor, WhisperForConditionalGeneration
import librosa
processor = WhisperProcessor.from_pretrained("Neurai/NeuraSpeech_WhisperBase")
model = WhisperForConditionalGeneration.from_pretrained("Neurai/NeuraSpeech_WhisperBase")
forced_decoder_ids = processor.get_decoder_prompt_ids(language="fa", task="transcribe")
def transcribe(audio):
if audio is None:
return "No audio input provided. Please record or upload an audio file."
sample_rate, array = audio
sr = 16000
array = librosa.to_mono(array)
array = librosa.resample(array, orig_sr=sample_rate, target_sr=16000)
input_features = processor(array, sampling_rate=sr, 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=True)
return transcription
# input_audio = gr.Audio(
# sources=["microphone"],
# waveform_options=gr.WaveformOptions(
# waveform_color="#01C6FF",
# waveform_progress_color="#0066B4",
# skip_length=2,
# show_controls=True,
# ),
# )
# demo = gr.Interface(
# fn=reverse_audio,
# inputs=input_audio,
# outputs="text"
# )
demo = gr.Interface(
fn=transcribe,
inputs=[gr.Audio(sources=["microphone"])],
outputs="text"
)
if __name__ == "__main__":
demo.launch()
|