| script_path = os.path.join(uroman_path, "bin", "uroman.pl") | |
| command = ["perl", script_path] | |
| process = subprocess.Popen(command, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) | |
| # Execute the perl command | |
| stdout, stderr = process.communicate(input=input_string.encode()) | |
| if process.returncode != 0: | |
| raise ValueError(f"Error {process.returncode}: {stderr.decode()}") | |
| # Return the output as a string and skip the new-line character at the end | |
| return stdout.decode()[:-1] | |
| text = "이봐 무슨 일이야" | |
| uromaized_text = uromanize(text, uroman_path=os.environ["UROMAN"]) | |
| inputs = tokenizer(text=uromaized_text, return_tensors="pt") | |
| set_seed(555) # make deterministic | |
| with torch.no_grad(): | |
| outputs = model(inputs["input_ids"]) | |
| waveform = outputs.waveform[0] | |
| Tips: | |
| The MMS-TTS checkpoints are trained on lower-cased, un-punctuated text. |