File size: 1,003 Bytes
7e6e084
 
cf20a06
0b960f8
7e6e084
 
cf20a06
 
 
 
d4dffb9
 
 
cf20a06
 
d08907e
7e6e084
 
 
 
 
 
 
 
 
 
ca8157c
 
 
 
7e6e084
 
 
 
 
 
 
 
 
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
import gradio as gr
from transformers import pipeline
from librosa import resample
import numpy as np

def transcribe(input_audio):
    sr, speech = input_audio
    # Convert to mono if stereo
    if speech.ndim > 1:
        speech = speech.mean(axis=1)
    # Convert to float32 if needed
    if speech.dtype != "float32":
        speech = speech.astype(np.float32)
    # Resample if sampling rate is not 16kHz
    if sr!=16000:
        speech = resample(speech, orig_sr=sr, target_sr=16000)
    output = pipe(speech, chunk_length_s=30, stride_length_s=5)['text']
    return output

pipe = pipeline(
    "automatic-speech-recognition",
    model="GetmanY1/wav2vec2-large-sami-cont-pt-22k-finetuned",
    device="cpu"
    )

gradio_app = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources=["upload","microphone"]),
    outputs="text",
    title="Sámi Automatic Speech Recognition",
)

if __name__ == "__main__":
    gradio_app.launch()



# if __name__ == "__main__":
#     gradio_app.launch()