File size: 951 Bytes
79c905a df3ff36 79c905a 75ffc04 79c905a 0c7bfc1 79c905a 0c7bfc1 79c905a 0c7bfc1 79c905a 0c7bfc1 79c905a |
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 |
import os
import gradio as gr
import whisper
model = whisper.load_model("small")
print(model.device)
def inference(audio):
audio = whisper.load_audio(audio)
audio = whisper.pad_or_trim(audio)
mel = whisper.log_mel_spectrogram(audio).to(model.device)
_, probs = model.detect_language(mel)
options = whisper.DecodingOptions(fp16 = False)
result = whisper.decode(model, mel, options)
print(result.text)
return result.text
block = gr.Blocks()
with block:
with gr.Group():
with gr.Box():
with gr.Row():
audio = gr.Audio(
label="Input Audio",
source="microphone",
type="filepath"
)
btn = gr.Button("Transcribe")
text = gr.Textbox()
btn.click(inference, inputs=[audio], outputs=[text], api_name="transcribe")
block.launch() |