# before
torch.hub.load(repo_or_dir='snakers4/silero-models',
               model='silero_stt',  # or silero_tts or silero_te
               **kwargs)

# after
from silero import silero_stt, silero_tts, silero_te
silero_stt(**kwargs)

import torch
import zipfile
import torchaudio
from glob import glob

device = torch.device('cpu')  # gpu also works, but our models are fast enough for CPU
model, decoder, utils = torch.hub.load(repo_or_dir='snakers4/silero-models',
                                       model='silero_stt',
                                       language='en', # also available 'de', 'es'
                                       device=device)
(read_batch, split_into_batches,
 read_audio, prepare_model_input) = utils  # see function signature for details

# download a single file in any format compatible with TorchAudio
torch.hub.download_url_to_file('https://opus-codec.org/static/examples/samples/speech_orig.wav',
                               dst ='speech_orig.wav', progress=True)
test_files = glob('speech_orig.wav')
batches = split_into_batches(test_files, batch_size=10)
input = prepare_model_input(read_batch(batches[0]),
                            device=device)

output = model(input)
for example in output:
    print(decoder(example.cpu()))

import onnx
import torch
import onnxruntime
from omegaconf import OmegaConf

language = 'en' # also available 'de', 'es'

# load provided utils
_, decoder, utils = torch.hub.load(repo_or_dir='snakers4/silero-models', model='silero_stt', language=language)
(read_batch, split_into_batches,
 read_audio, prepare_model_input) = utils

# see available models
torch.hub.download_url_to_file('https://raw.githubusercontent.com/snakers4/silero-models/master/models.yml', 'models.yml')
models = OmegaConf.load('models.yml')
available_languages = list(models.stt_models.keys())
assert language in available_languages

# load the actual ONNX model
torch.hub.download_url_to_file(models.stt_models.en.latest.onnx, 'model.onnx', progress=True)
onnx_model = onnx.load('model.onnx')
onnx.checker.check_model(onnx_model)
ort_session = onnxruntime.InferenceSession('model.onnx')

# download a single file in any format compatible with TorchAudio
torch.hub.download_url_to_file('https://opus-codec.org/static/examples/samples/speech_orig.wav', dst ='speech_orig.wav', progress=True)
test_files = ['speech_orig.wav']
batches = split_into_batches(test_files, batch_size=10)
input = prepare_model_input(read_batch(batches[0]))

# actual ONNX inference and decoding
onnx_input = input.detach().cpu().numpy()
ort_inputs = {'input': onnx_input}
ort_outs = ort_session.run(None, ort_inputs)
decoded = decoder(torch.Tensor(ort_outs[0])[0])
print(decoded)

import os
import torch
import subprocess
import tensorflow as tf
import tensorflow_hub as tf_hub
from omegaconf import OmegaConf

language = 'en' # also available 'de', 'es'

# load provided utils using torch.hub for brevity
_, decoder, utils = torch.hub.load(repo_or_dir='snakers4/silero-models', model='silero_stt', language=language)
(read_batch, split_into_batches,
 read_audio, prepare_model_input) = utils

# see available models
torch.hub.download_url_to_file('https://raw.githubusercontent.com/snakers4/silero-models/master/models.yml', 'models.yml')
models = OmegaConf.load('models.yml')
available_languages = list(models.stt_models.keys())
assert language in available_languages

# load the actual tf model
torch.hub.download_url_to_file(models.stt_models.en.latest.tf, 'tf_model.tar.gz')
subprocess.run('rm -rf tf_model && mkdir tf_model && tar xzfv tf_model.tar.gz -C tf_model',  shell=True, check=True)
tf_model = tf.saved_model.load('tf_model')

# download a single file in any format compatible with TorchAudio
torch.hub.download_url_to_file('https://opus-codec.org/static/examples/samples/speech_orig.wav', dst ='speech_orig.wav', progress=True)
test_files = ['speech_orig.wav']
batches = split_into_batches(test_files, batch_size=10)
input = prepare_model_input(read_batch(batches[0]))

# tf inference
res = tf_model.signatures["serving_default"](tf.constant(input.numpy()))['output_0']
print(decoder(torch.Tensor(res.numpy())[0]))

# V4
import torch

language = 'ru'
model_id = 'v4_ru'
sample_rate = 48000
speaker = 'xenia'
device = torch.device('cpu')

model, example_text = torch.hub.load(repo_or_dir='snakers4/silero-models',
                                     model='silero_tts',
                                     language=language,
                                     speaker=model_id)
model.to(device)  # gpu or cpu

audio = model.apply_tts(text=example_text,
                        speaker=speaker,
                        sample_rate=sample_rate)

# V4
import os
import torch

device = torch.device('cpu')
torch.set_num_threads(4)
local_file = 'model.pt'

if not os.path.isfile(local_file):
    torch.hub.download_url_to_file('https://models.silero.ai/models/tts/ru/v4_ru.pt',
                                   local_file)  

model = torch.package.PackageImporter(local_file).load_pickle("tts_models", "model")
model.to(device)

example_text = 'В недрах тундры выдры в г етрах т ырят в вёдра ядра кедров.'
sample_rate = 48000
speaker='baya'

audio_paths = model.save_wav(text=example_text,
                             speaker=speaker,
                             sample_rate=sample_rate)

# V3
import torch
from aksharamukha import transliterate

# Loading model
model, example_text = torch.hub.load(repo_or_dir='snakers4/silero-models',
                                     model='silero_tts',
                                     language='indic',
                                     speaker='v4_indic')

orig_text = "प्रसिद्द कबीर अध्येता, पुरुषोत्तम अग्रवाल का यह शोध आलेख, उस रामानंद की खोज करता है"
roman_text = transliterate.process('Devanagari', 'ISO', orig_text)
print(roman_text)

audio = model.apply_tts(roman_text,
                        speaker='hindi_male')

import torch

model, example_texts, languages, punct, apply_te = torch.hub.load(repo_or_dir='snakers4/silero-models',
                                                                  model='silero_te')

input_text = input('Enter input text\n')
apply_te(input_text, lan='en')

import torch

name = 'small_slow'
device = torch.device('cpu')
model, samples, utils = torch.hub.load(
  repo_or_dir='snakers4/silero-models',
  model='silero_denoise',
  name=name,
  device=device)
(read_audio, save_audio, denoise) = utils

i = 0
torch.hub.download_url_to_file(
  samples[i],
  dst=f'sample{i}.wav',
  progress=True
)
audio_path = f'sample{i}.wav'
audio = read_audio(audio_path).to(device)
output = model(audio)
save_audio(f'result{i}.wav', output.squeeze(1).cpu())

i = 1
torch.hub.download_url_to_file(
  samples[i],
  dst=f'sample{i}.wav',
  progress=True
)
output, sr = denoise(model, f'sample{i}.wav', f'result{i}.wav', device='cpu')

import os
import torch

device = torch.device('cpu')
torch.set_num_threads(4)
local_file = 'model.pt'

if not os.path.isfile(local_file):
    torch.hub.download_url_to_file('https://models.silero.ai/denoise_models/sns_latest.jit',
                                   local_file)  

model = torch.jit.load(local_file)
torch._C._jit_set_profiling_mode(False) 
torch.set_grad_enabled(False)
model.to(device)

a = torch.rand((1, 48000))
a = a.to(device)
out = model(a)