Spaces:
Runtime error
Runtime error
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| import torch.optim as optim | |
| import torchaudio | |
| import torchaudio.functional as Fu | |
| import sys | |
| import matplotlib.pyplot as plt | |
| import IPython.display as ipd | |
| from tqdm import tqdm | |
| import gradio as gr | |
| import ffmpeg | |
| import resampy | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| sample_rate = 48000 | |
| new_sample_rate = 8000 | |
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| import torch.optim as optim | |
| import torchaudio | |
| import torchaudio.functional as Fu | |
| import sys | |
| import matplotlib.pyplot as plt | |
| import IPython.display as ipd | |
| from tqdm import tqdm | |
| import gradio as gr | |
| import ffmpeg | |
| import resampy | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| sample_rate = 48000 | |
| new_sample_rate = 8000 | |
| class M5(nn.Module): | |
| def __init__(self, n_input=1, n_output=35, stride=16, n_channel=32): | |
| super().__init__() | |
| self.conv1 = nn.Conv1d(n_input, n_channel, kernel_size=80, stride=stride) | |
| self.bn1 = nn.BatchNorm1d(n_channel) | |
| self.pool1 = nn.MaxPool1d(4) | |
| self.conv2 = nn.Conv1d(n_channel, n_channel, kernel_size=3) | |
| self.bn2 = nn.BatchNorm1d(n_channel) | |
| self.pool2 = nn.MaxPool1d(4) | |
| self.conv3 = nn.Conv1d(n_channel, 2 * n_channel, kernel_size=3) | |
| self.bn3 = nn.BatchNorm1d(2 * n_channel) | |
| self.pool3 = nn.MaxPool1d(4) | |
| self.conv4 = nn.Conv1d(2 * n_channel, 2 * n_channel, kernel_size=3) | |
| self.bn4 = nn.BatchNorm1d(2 * n_channel) | |
| self.pool4 = nn.MaxPool1d(4) | |
| self.fc1 = nn.Linear(2 * n_channel, n_output) | |
| def forward(self, x): | |
| x = self.conv1(x) | |
| x = F.relu(self.bn1(x)) | |
| x = self.pool1(x) | |
| x = self.conv2(x) | |
| x = F.relu(self.bn2(x)) | |
| x = self.pool2(x) | |
| x = self.conv3(x) | |
| x = F.relu(self.bn3(x)) | |
| x = self.pool3(x) | |
| x = self.conv4(x) | |
| x = F.relu(self.bn4(x)) | |
| x = self.pool4(x) | |
| x = F.avg_pool1d(x, x.shape[-1]) | |
| x = x.permute(0, 2, 1) | |
| x = self.fc1(x) | |
| return F.log_softmax(x, dim=2) | |
| def get_likely_index(tensor): | |
| # find most likely label index for each element in the batch | |
| return tensor.argmax(dim=-1) | |
| def index_to_label(index): | |
| # Return the word corresponding to the index in labels | |
| # This is the inverse of label_to_index | |
| return labels[index] | |
| def predict(filepath): | |
| tensor,sample_rate = torchaudio.load(filepath) | |
| transformchannels = torchaudio.transforms.MuLawEncoding(quantization_channels=1) | |
| tensor= transformchannels (tensor) | |
| tensor = tensor.to(device) | |
| tensor = tensor.type(torch.LongTensor) | |
| #transform = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=new_sample_rate) | |
| #tensor = transform(tensor) | |
| tensor = model(tensor.unsqueeze(0)) | |
| #tensor = get_likely_index(tensor) | |
| #tensor = index_to_label(tensor.squeeze()) | |
| #return tensor | |
| return tensor | |
| model = torch.load('export.pkl',map_location=torch.device('cpu')) | |
| gr.Interface(fn=predict, inputs=gr.inputs.Audio(source='microphone',type='filepath'), outputs='text').launch(share=False) | |
| def get_likely_index(tensor): | |
| # find most likely label index for each element in the batch | |
| return tensor.argmax(dim=-1) | |
| def index_to_label(index): | |
| # Return the word corresponding to the index in labels | |
| # This is the inverse of label_to_index | |
| return labels[index] | |
| def predict(filepath): | |
| tensor,sample_rate = torchaudio.load(filepath) | |
| transformchannels = torchaudio.transforms.MuLawEncoding(quantization_channels=1) | |
| tensor= transformchannels (tensor) | |
| tensor = tensor.to(device) | |
| tensor = tensor.type(torch.LongTensor) | |
| transform = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=new_sample_rate) | |
| tensor = transform(tensor) | |
| tensor = model(tensor.unsqueeze(0)) | |
| tensor = get_likely_index(tensor) | |
| tensor = index_to_label(tensor.squeeze()) | |
| return tensor | |
| model = torch.load('export.pkl',map_location=torch.device('cpu')) | |
| gr.Interface(fn=predict, inputs=gr.inputs.Audio(source='microphone',type='filepath'), outputs='text').launch(share=False) |