File size: 1,276 Bytes
3b35aeb |
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 |
import torch
import torchaudio
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import gradio as gr
model = Wav2Vec2ForCTC.from_pretrained("tacab/tacab_asr_somali")
processor = Wav2Vec2Processor.from_pretrained("tacab/tacab_asr_somali")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
def transcribe(audio_path):
waveform, sample_rate = torchaudio.load(audio_path)
if sample_rate != 16000:
waveform = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)(waveform)
if waveform.shape[0] > 1:
waveform = waveform.mean(dim=0, keepdim=True)
inputs = processor(waveform.squeeze().numpy(), sampling_rate=16000, return_tensors="pt")
input_values = inputs.input_values.to(device)
with torch.no_grad():
logits = model(input_values).logits
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)[0]
return transcription.lower()
iface = gr.Interface(
fn=transcribe,
inputs=gr.Audio(type="filepath", label="🎙️ Somali Audio"),
outputs=gr.Text(label="📄 Transcription"),
title="Tacab Somali ASR",
description="Speak Somali and get transcription back!",
)
iface.launch(server_name="0.0.0.0") |