File size: 832 Bytes
db9a501 a95b4f8 2edd588 a95b4f8 2edd588 a95b4f8 1f6c393 a95b4f8 2edd588 db9a501 a95b4f8 2edd588 51a2f53 2edd588 |
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 |
from transformers import pipeline
model_id = "sanchit-gandhi/whisper-small-dv" # update with your model id
pipe = pipeline("automatic-speech-recognition", model=model_id)
def transcribe_speech(filepath):
output = pipe(
filepath,
max_new_tokens=256,
generate_kwargs={
"task": "transcribe",
"language": "sinhalese",
}, # update with the language you've fine-tuned on
chunk_length_s=30,
batch_size=8,
)
return output["text"]
import gradio as gr
demo = gr.Blocks()
mic_transcribe = gr.Interface(
fn=transcribe_speech,
inputs=gr.Audio(sources="microphone", type="filepath"),
outputs=gr.outputs.Textbox(),
)
with demo:
gr.TabbedInterface(
[mic_transcribe],
["Transcribe Microphone"],
)
demo.launch(debug=True) |