---
language:
- uk
- ru
library_name: nemo
tags:
- deepspeech
---

# list models


### QuartzNet15x5

---
- 2023-04-28
  - _language:_ ru
  - _from_pretrained:_ [stt_en_quartznet15x5](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_quartznet15x5)
  - _Epoch:_ 50
  - _Step:_ 738649
  - _val_loss:_ 4.19466 (best 4.19466)
  - _model:_ ```quartznet15x5/2023-04-28_00-24-37/stt_ru_quartznet15x5.nemo```
  - _last checkpoint:_ ```quartznet15x5/2023-04-28_00-24-37/stt_ru_quartznet15x5--val_loss=4.2732-epoch=50-last.ckpt```
  - _Dataset train:_ **709100** files totalling **680.21** hours
  - _Dataset validation:_ **14670** files totalling **15.63** hours
- 2023-04-04
  - _language:_ uk
  - _from_pretrained:_ [stt_en_quartznet15x5](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_quartznet15x5)
  - _Epoch:_ 34
  - _Step:_ 566076
  - _val_loss:_ 1.90886 (best 1.89907)
  - _model:_ ```quartznet15x5/2023-04-04_02-57-02/stt_uk_quartznet15x5.nemo```
  - _last checkpoint:_ ```quartznet15x5/2023-04-04_02-57-02/QuartzNet15x5--val_loss=1.9543-epoch=34-last.ckpt```
  - _Dataset train:_ **1042635** files totalling **1028.14** hours
  - _Dataset validation:_ **50640** files totalling **50.71** hours
- 2023-02-23
  - _language:_ uk-RU
  - _from_pretrained:_ [stt_en_quartznet15x5](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_quartznet15x5)
  - _Epoch:_ 7
  - _Step:_ 217287
  - _val_loss:_ 1.66200 (best 1.66200)
  - _model:_ ```quartznet15x5/2023-02-23_11-43-23/stt_uk_ru_quartznet15x5.nemo```
  - _last checkpoint:_ ```quartznet15x5/2023-02-23_11-43-23/QuartzNet15x5--val_loss=1.6620-epoch=7-last.ckpt```
  - _Dataset train:_ **1738252** files totalling **1645.74** hours
  - _Dataset validation:_ **11373** files totalling **12.63** hours


### Jasper10x5

---
- 2023-04-07
  - _language:_ uk
  - _from_pretrained:_ [stt_en_jasper10x5dr](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_jasper10x5dr)
  - _Epoch:_ 17
  - _Step:_ 293256
  - _val_loss:_ 2.10919 (best 2.10919)
  - _model:_ ```jasper10x5/2023-04-07_05-01-29/stt_uk_jasper10x5.nemo```
  - _last checkpoint:_ ```jasper10x5/2023-04-07_05-01-29/Jasper10x5--val_loss=2.1092-epoch=17-last.ckpt```
  - _Dataset train:_ **1042635** files totalling **1028.14** hours
  - _Dataset validation:_ **50640** files totalling **50.71** hours
- 2023-02-22
  - _language:_ uk-RU
  - _from_pretrained:_ [stt_en_jasper10x5dr](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_jasper10x5dr)
  - _Epoch:_ 4
  - _Step:_ 271604
  - _val_loss:_ 1.76058 (best 1.76058)
  - _model:_ ```jasper10x5/2023-02-22_06-46-21/stt_uk_ru_jasper10x5.nemo```
  - _last checkpoint:_ ```jasper10x5/2023-02-22_06-46-21/Jasper10x5--val_loss=1.7606-epoch=4-last.ckpt```
  - _Dataset train:_ **1738252** files totalling **1645.74** hours
  - _Dataset validation:_ **11373** files totalling **12.63** hours


# Punctuation and Capitalization Model

### punctuation_uk_bert 

---
- 2023-06-28
  - _language:_ uk
  - _Epoch:_ 3
  - _val_loss:_ 0.0319
  - _last checkpoint:_ ```punctuation_uk_bert/2023-06-28_04-10-06/punctuation_uk_bert--val_loss=0.0385-epoch=3-last.ckpt```


### punctuation_ru_bert 

---
- 2023-06-28
  - _language:_ rU
  - _Epoch:_ 5
  - _val_loss:_ 0.0196
  - _last checkpoint:_ ```punctuation_ru_bert/2023-06-28_15-12-29/punctuation_ru_bert--val_loss=0.0712-epoch=5-last.ckpt```


### Використання ASR:
```python
from huggingface_hub import hf_hub_download
from nemo.collections.asr.models import ASRModel
from omegaconf import OmegaConf


# filename_model = 'quartznet15x5/2023-02-23_11-43-23/stt_uk_ru_quartznet15x5.nemo'
# filename_model = 'quartznet15x5/2023-04-04_02-57-02/stt_uk_quartznet15x5.nemo'
# filename_model = 'jasper10x5/2023-02-22_06-46-21/stt_uk_ru_jasper10x5.nemo'
filename_model = 'jasper10x5/2023-04-07_05-01-29/stt_uk_jasper10x5.nemo'

model_path = hf_hub_download(
  repo_id="u107/nemo",
  filename=filename_model,
  repo_type="model",
  cache_dir='/content',
  use_auth_token='hf_...')

nemo_model = ASRModel.restore_from(
  restore_path=model_path,
  # map_location='CPU',
  # return_config=True,
)  # type: ASRModel

# зберегти файл налаштувань
OmegaConf.save(nemo_model.cfg, 'model_config.yaml')

# відобразити версію nemo на якій було навчання
print(nemo_model.cfg.nemo_version)

# відобразити алфавіт
print(nemo_model.cfg.labels)
```

### Використання NLP:
```python
from huggingface_hub import hf_hub_download
from nemo.collections import nlp as nemo_nlp


# filename_model = 'punctuation_ru_bert/2023-06-28_15-12-29/punctuation_ru_bert.nemo'
filename_model = 'punctuation_uk_bert/2023-06-28_04-10-06/punctuation_uk_bert.nemo'

model_path = hf_hub_download(
  repo_id="u107/nemo",
  filename=filename_model,
  repo_type="model",
  cache_dir='/content',
  use_auth_token='hf_...')

pretrained_model = nemo_nlp.models.PunctuationCapitalizationModel.restore_from(
  restore_path=model_path
)

queries = [
  'ніхто ж не каже що б давати так',
]

result = pretrained_model.add_punctuation_capitalization(queries=queries)

print(result)
```