YAML Metadata
Warning:
The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
def word_to_morph_features(text):
prefix = "<word analyze>: "
inputs = tokenizer(prefix + text, return_tensors="pt", max_length=128, truncation=True)
device = model.device
inputs = {k: v.to(device) for k, v in inputs.items()}
outputs = model.generate(**inputs)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
test_words = [
'зезгъэщхьырт',
'псыхьыжауэ',
'хъужами',
'япыщIат',
'къыщежьэри',
'схъумэрт',
'щхьэпэщ',
'сылъакъуэ',
'къеджэмэ',
'гъэщам',
'бэракъыу',
'уеупщIакъым',
'къэзыгъэпэж',
'къахуэбла',
'иращIэнтэкъым',
'къыбоух',
'гъусари',
'сщитIэгъащ',
'дытелажьэу',
]
for word in test_words:
features = word_to_morph_features(word)
print(f"{word} -> {features}")
зезгъэщхьырт -> <features>: 1sg-pre-1sg-caus-know-past
псыхьыжауэ -> <features>: water-water-adv
хъужами -> <features>: become-past-conn
япыщIат -> <features>: 3pl-attach-past-aff
къыщежьэри -> <features>: hor-begin-and
схъумэрт -> <features>: 1sg-caus-stand-epv-fut
щхьэпэщ -> <features>: dir-ben-val-aff
сылъакъуэ -> <features>: 1sg-run-adv
къеджэмэ -> <features>: hor-read-cond
гъэщам -> <features>: year-erg
бэракъыу -> <features>: flag-adv
уеупщIакъым -> <features>: 2sg-ben-ask-neg
къэзыгъэпэж -> <features>: hor-rel-caus-caus-run-back
къахуэбла -> <features>: hor-ben-loc-approach
иращIэнтэкъым -> <features>: 3pl-ben-3pl-do-epv-fut-neg
къыбоух -> <features>: 2sg-dir-2sg-caus-fall
гъусари -> <features>: companion-and
сщитIэгъащ -> <features>: 1sg-ben-1sg-put-past
дытелажьэу -> <features>: 1pl-dir-work-adv
- Downloads last month
- 3
Model tree for panagoa/nllb-200-based-kbd-morphologizer
Base model
facebook/nllb-200-distilled-600M
Finetuned
panagoa/nllb-200-distilled-600M-kbd-v0.1