Iarfmoose

Rank:

Average Model Cost: $0.0000

Number of Runs: 10,027

Models by this creator

t5-base-question-generator

t5-base-question-generator

iarfmoose

The t5-base-question-generator model is a sequence-to-sequence question generator that takes an answer and context as input and generates a question as output. It is based on a pretrained t5-base model. The model works best with full sentence answers but can also handle single word or short phrase answers. It is trained to generate reading comprehension-style questions with answers extracted from a text. The model has limitations such as potentially reflecting biases present in the context and generating incoherent questions if the context is too short or absent, or if the context and answer do not match. The model was fine-tuned on a dataset comprising several QA datasets and was trained for 20 epochs with a learning rate of 1e-3. The training procedure used a batch size of 4 due to GPU memory limitations.

Read more

$-/run

5.9K

Huggingface

roberta-small-bulgarian-pos

roberta-small-bulgarian-pos

RoBERTa-small-bulgarian-POS The RoBERTa model was originally introduced in this paper. This model is a version of RoBERTa-small-Bulgarian fine-tuned for part-of-speech tagging. Intended uses The model can be used to predict part-of-speech tags in Bulgarian text. Since the tokenizer uses byte-pair encoding, each word in the text may be split into more than one token. When predicting POS-tags, the last token from each word can be used. Using the last token was found to slightly outperform predictions based on the first token. An example of this can be found here. Limitations and bias The pretraining data is unfiltered text from the internet and may contain all sorts of biases. Training data In addition to the pretraining data used in RoBERTa-base-Bulgarian, the model was trained on the UPOS tags from (UD_Bulgarian-BTB)[https://github.com/UniversalDependencies/UD_Bulgarian-BTB]. Training procedure The model was trained for 5 epochs over the training set. The loss was calculated based on label predictions for the last POS-tag for each word. The model achieves 98% on the test set.

Read more

$-/run

115

Huggingface

wav2vec2-large-xlsr-frisian

wav2vec2-large-xlsr-frisian

Wav2Vec2-Large-XLSR-53-Frisian Fine-tuned facebook/wav2vec2-large-xlsr-53 in Frisian using the Common Voice When using this model, make sure that your speech input is sampled at 16kHz. Usage The model can be used directly (without a language model) as follows: Evaluation The model can be evaluated as follows on the Frisian test data of Common Voice. Test Result: 21.72 % Training The Common Voice train, validation datasets were used for training. The script used for training can be found here A notebook of the evaluation script can be found here

Read more

$-/run

17

Huggingface

wav2vec2-large-xlsr-sorbian

wav2vec2-large-xlsr-sorbian

Wav2Vec2-Large-XLSR-53-Sorbian Fine-tuned facebook/wav2vec2-large-xlsr-53 in Sorbian using the Common Voice When using this model, make sure that your speech input is sampled at 16kHz. Usage The model can be used directly (without a language model) as follows: Evaluation The model can be evaluated as follows on the Sorbian test data of Common Voice. Test Result: 41.74 % Training The Common Voice train, validation datasets were used for training. The script used for training can be found here A notebook of the evaluation script can be found here

Read more

$-/run

10

Huggingface

Similar creators