|
import time |
|
from transformers import pipeline |
|
import gradio as gr |
|
import numpy as np |
|
import librosa |
|
|
|
transcriber_hindi = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec-hindi") |
|
transcriber_bengali = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_bengali") |
|
transcriber_odia = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec-odia") |
|
transcriber_gujarati = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_gujarati") |
|
|
|
|
|
transcriber_telugu = pipeline("automatic-speech-recognition", model="krishnateja/wav2vec2-telugu_150") |
|
|
|
|
|
transcriber_tamil = pipeline("automatic-speech-recognition", model="Amrrs/wav2vec2-large-xlsr-53-tamil") |
|
|
|
|
|
transcriber_kannada = pipeline("automatic-speech-recognition", model="TheAIchemist13/kannada_beekeeping_wav2vec2") |
|
|
|
languages = ["hindi","bengali","odia","gujarati","telugu","tamil","kannada"] |
|
|
|
def resample_to_16k(audio, orig_sr): |
|
y_resampled = librosa.resample(y=audio, orig_sr=orig_sr, target_sr=16000) |
|
return y_resampled |
|
|
|
def transcribe(audio,lang="hindi"): |
|
sr,y = audio |
|
y = y.astype(np.float32) |
|
y/= np.max(np.abs(y)) |
|
y_resampled = resample_to_16k(y,sr) |
|
if lang not in languages: |
|
return "No Model","So Stay tuned!" |
|
pipe= eval(f'transcriber_{lang}') |
|
start_time = time.time() |
|
trans = pipe(y_resampled) |
|
end_time = time.time() |
|
|
|
return trans["text"],(end_time-start_time) |
|
|
|
demo = gr.Interface( |
|
transcribe, |
|
inputs=["microphone",gr.Radio(["hindi","bengali","odia","gujarati","telugu","tamil","kannada"],value="hindi")], |
|
|
|
outputs=["text","text"], |
|
examples=[["./Samples/Hindi_1.mp3","hindi"],["./Samples/Hindi_2.mp3","hindi"],["./Samples/Hindi_3.mp3","hindi"],["./Samples/Hindi_4.mp3","hindi"],["./Samples/Hindi_5.mp3","hindi"],["./Samples/Tamil_2.mp3","hindi"],["./Samples/climate ex short.wav","hindi"],["./Samples/Gujarati_1.wav","gujarati"],["./Samples/Gujarati_2.wav","gujarati"],["./Samples/Bengali_1.wav","bengali"],["./Samples/Bengali_2.wav","bengali"],["./Samples/kannada.wav","kannada"]]) |
|
|
|
demo.launch() |
