| import soundfile as sf | |
| import torch | |
| from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor | |
| import gradio as gr | |
| def parse_transcription(wav_file): | |
| print("hello") | |
| audio_input, sample_rate = sf.read(wav_file.name) | |
| input_values = processor(audio_input, sampling_rate=sample_rate, return_tensors="pt").input_values | |
| logits = model(input_values).logits | |
| predicted_ids = torch.argmax(logits, dim=-1) | |
| transcription = processor.decode(predicted_ids[0], skip_special_tokens=True) | |
| return transcription | |
| processor = Wav2Vec2Processor.from_pretrained("Harveenchadha/vakyansh-wav2vec2-hindi-him-4200") | |
| model = Wav2Vec2ForCTC.from_pretrained("Harveenchadha/vakyansh-wav2vec2-hindi-him-4200") | |
| input_ = gr.inputs.Audio(source="microphone", type="file") | |
| gr.Interface(parse_transcription, inputs = input_, outputs="text", | |
| analytics_enabled=False, show_tips=False, enable_queue=True).launch(inline=False); |