Spaces:
Runtime error
Runtime error
| from transformers import pipeline | |
| asr_pipe = pipeline("automatic-speech-recognition", model="ihanif/whisper-medium-urdu") | |
| from difflib import SequenceMatcher | |
| # List of commands | |
| commands = [ | |
| "کمپیوٹر، کھیل کھیلو", | |
| "میوزک چلاؤ", | |
| "روشنی کم کریں" | |
| ] | |
| replies = [ | |
| "https://medicobilling.info/urdu.wav", | |
| "download.wav", | |
| "https://medicobilling.info/urdu.wav" | |
| ] | |
| # Function to find the most similar command | |
| def find_most_similar_command(statement, command_list): | |
| best_match = None | |
| highest_similarity = 0 | |
| i=0 | |
| for command in command_list: | |
| similarity = SequenceMatcher(None, statement, command).ratio() | |
| if similarity > highest_similarity: | |
| highest_similarity = similarity | |
| best_match = command | |
| reply=replies[i] | |
| i+=1 | |
| else: | |
| best_match="unknown" | |
| reply="unknown.wav" | |
| return best_match,reply | |
| def transcribe_the_command(audio): | |
| import soundfile as sf | |
| sample_rate, audio_data = audio | |
| file_name = "recorded_audio.wav" | |
| sf.write(file_name, audio_data, sample_rate) | |
| # Convert stereo to mono by averaging the two channels | |
| print(file_name) | |
| transcript = asr_pipe(file_name)["text"] | |
| most_similar_command,reply = find_most_similar_command(transcript, commands) | |
| print(f"Given Statement: {transcript}") | |
| print(f"Most Similar Command: {most_similar_command}\n") | |
| return reply | |
| # get_text_from_voice("urdu.wav") | |
| import gradio as gr | |
| iface = gr.Interface( | |
| fn=transcribe_the_command, | |
| inputs=gr.inputs.Audio(label="Recorded Audio"), | |
| outputs="text", | |
| title="Whisper Small Hindi", | |
| description="Realtime demo for Hindi speech recognition using a fine-tuned Whisper small model.", | |
| ) | |
| iface.launch() |