Spaces:
Running
Running
File size: 2,533 Bytes
28d0c5f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
import torch
import torch.nn as nn
import pickle
import pickle
def getASRModel(language: str) -> nn.Module:
if language == 'de':
model, decoder, utils = torch.hub.load(repo_or_dir='snakers4/silero-models',
model='silero_stt',
language='de',
device=torch.device('cpu'))
elif language == 'en':
model, decoder, utils = torch.hub.load(repo_or_dir='snakers4/silero-models',
model='silero_stt',
language='en',
device=torch.device('cpu'))
elif language == 'fr':
model, decoder, utils = torch.hub.load(repo_or_dir='snakers4/silero-models',
model='silero_stt',
language='fr',
device=torch.device('cpu'))
return (model, decoder)
def getTTSModel(language: str) -> nn.Module:
if language == 'de':
speaker = 'thorsten_v2' # 16 kHz
model, _ = torch.hub.load(repo_or_dir='snakers4/silero-models',
model='silero_tts',
language=language,
speaker=speaker)
elif language == 'en':
speaker = 'lj_16khz' # 16 kHz
model = torch.hub.load(repo_or_dir='snakers4/silero-models',
model='silero_tts',
language=language,
speaker=speaker)
else:
raise ValueError('Language not implemented')
return model
def getTranslationModel(language: str) -> nn.Module:
from transformers import AutoTokenizer
from transformers import AutoModelForSeq2SeqLM
if language == 'de':
model = AutoModelForSeq2SeqLM.from_pretrained(
"Helsinki-NLP/opus-mt-de-en")
tokenizer = AutoTokenizer.from_pretrained(
"Helsinki-NLP/opus-mt-de-en")
# Cache models to avoid Hugging face processing
with open('translation_model_de.pickle', 'wb') as handle:
pickle.dump(model, handle)
with open('translation_tokenizer_de.pickle', 'wb') as handle:
pickle.dump(tokenizer, handle)
else:
raise ValueError('Language not implemented')
return model, tokenizer
|