nemo-toolkit

import nemo.collections.asr as nemo_asr # This will download and load the pretrained model from NVIDIA's NGC cloud # The first run takes time to download the model (~1.5 GB) asr_model = nemo_asr.models.EncDecRNNTModel.from_pretrained(model_name="stt_en_fastconformer_hybrid_large_ctc_rnnt") # Path to an audio file (replace with your own or download an example) # For demonstration, we'll use a placeholder. In a real scenario, you'd have an actual .wav file. # Example audio can be found in NeMo's tutorials or downloaded from public datasets. # For example: !wget https://nemo-public.s3.us-east-2.amazonaws.com/example_samples/audio_0.wav filepath = "./audio_0.wav" # Ensure this file exists for the code to run # For demonstration, let's create a dummy file if it doesn't exist import os if not os.path.exists(filepath): try: import torchaudio import torch sample_rate = 16000 duration_seconds = 5 waveform = torch.sin(2 * torch.pi * 440 * torch.arange(0, sample_rate * duration_seconds) / sample_rate).unsqueeze(0) torchaudio.save(filepath, waveform, sample_rate) print(f"Created dummy audio file: {filepath}") except ImportError: print(f"Warning: '{filepath}' not found and torchaudio not installed to create a dummy file. Quickstart may fail.") transcriptions = asr_model.transcribe([filepath]) print(f"Transcription: {transcriptions[0]}")