utrobinmv

10 models • 1 total models in database
Sort by:

t5_translate_en_ru_zh_small_1024

T5 English, Russian and Chinese multilingual machine translation This model represents a conventional T5 transformer in multitasking mode for translation into the required language, precisely configured for machine translation for pairs: ru-zh, zh-ru, en-zh, zh-en, en-ru, ru-en. The model can perform direct translation between any pair of Russian, Chinese or English languages. For translation into the target language, the target language identifier is specified as a prefix 'translate to :'. In this case, the source language may not be specified, in addition, the source text may be multilingual.

license:apache-2.0
21,207
38

tts_ru_free_hf_vits_low_multispeaker

license:apache-2.0
382
20

t5_translate_en_ru_zh_large_1024

T5 English, Russian and Chinese multilingual machine translation This model represents a conventional T5 transformer in multitasking mode for translation into the required language, precisely configured for machine translation for pairs: ru-zh, zh-ru, en-zh, zh-en, en-ru, ru-en. The model can perform direct translation between any pair of Russian, Chinese or English languages. For translation into the target language, the target language identifier is specified as a prefix 'translate to :'. In this case, the source language may not be specified, in addition, the source text may be multilingual.

license:apache-2.0
282
86

tts_ru_free_hf_vits_high_multispeaker

license:apache-2.0
268
11

t5_summary_en_ru_zh_large_2048

NaNK
license:apache-2.0
151
3

t5_summary_en_ru_zh_base_2048

T5 model for multilingual text Summary in English, Russian and Chinese language This model is designed to perform the task of controlled generation of summary text content in multitasking mode with a built-in translation function for languages: Russian, Chinese, English. This is the T5 multitasking model. Which has a conditionally controlled ability to generate summary text content, and translate this. In total, she understands 12 commands, according to the set prefix: 1) "summary: " - to generate simple concise content in the source language 2) "summary brief: " - to generate a shortened summary content in the source language 3) "summary big: " - to generate elongated summary content in the source language The model can understand text in any language from the list: Russian, Chinese or English. It can also translate the result into any language from the list: Russian, Chinese or English. For translation into the target language, the target language identifier is specified as a prefix "... to :". Where lang can take the values: ru, en, zh. The source language may not be specified, in addition, the source text may be multilingual. 4) "summary to en: " - to generate summary content in English from multilingual text 5) "summary brief to en: " - to generate a shortened summary of the content in English from multilingual text 6) "summary big to en: " - to generate elongated summary content in English from multilingual text 7) "summary to ru: " - to generate summary content in Russian from multilingual text 8) "summary brief to ru: " - to generate a shortened summary of the content in Russian from multilingual text 9) "summary big to ru: " - to generate elongated summary content in Russian from multilingual text 10) "summary to zh: " - to generate summary content in Chinese from multilingual text 11) "summary brief to zh: " - to generate a shortened summary of the content in Chinese from multilingual text 12) "summary big to zh: " - to generate elongated summary content in Chinese from multilingual text A training model for compressing a context of 2048 tokens and outputs a summary of up to 200 tokens in big task, 50 tokens in summary, and 20 tokens in brief task. Example resume for Chinese text on English language:

NaNK
license:apache-2.0
130
45

t5_translate_en_ru_zh_large_1024_v2

T5 English, Russian and Chinese multilingual machine translation This model represents a conventional T5 transformer in multitasking mode for translation into the required language, precisely configured for machine translation for pairs: ru-zh, zh-ru, en-zh, zh-en, en-ru, ru-en. The model can perform direct translation between any pair of Russian, Chinese or English languages. For translation into the target language, the target language identifier is specified as a prefix 'translate to :'. In this case, the source language may not be specified, in addition, the source text may be multilingual. Fine tune from the base model: utrobinmv/t5translateenruzhlarge1024 This version of the model was based on noisier data with a noise reduction function. The model can additionally insert punctuation marks into sentences if they are missing from the source text. This is convenient to use for translating texts after ASR models. The model has learned how to translate small markdown files while maintaining the markup and html tags.

NaNK
license:apache-2.0
106
36

t5_translate_en_ru_zh_base_200

T5 English, Russian and Chinese multilingual machine translation This model represents a conventional T5 transformer in multitasking mode for translation into the required language, precisely configured for machine translation for pairs: ru-zh, zh-ru, en-zh, zh-en, en-ru, ru-en. The model can perform direct translation between any pair of Russian, Chinese or English languages. For translation into the target language, the target language identifier is specified as a prefix 'translate to :'. In this case, the source language may not be specified, in addition, the source text may be multilingual.

license:apache-2.0
74
12

m2m_translate_en_ru_zh_large_4096

license:apache-2.0
15
2

t5_translate_en_ru_zh_base_200_sent

NaNK
license:apache-2.0
5
0