zulootrinity.blogg.se - Github perian daata

#GITHUB PERIAN DAATA HOW TO#
#GITHUB PERIAN DAATA LICENSE#

Performance Factorsįactors relevant to Speech-to-Text performance include but are not limited to speaker demographics, recording quality, and background noise. Speech-to-Text for the Persian Language on 16kHz, mono-channel audio.

Where to send questions or comments about the model: You can leave an issue on STT issues, open a new discussion on STT discussions, or chat with us on Gitter.

#GITHUB PERIAN DAATA LICENSE#

License: GNU Lesser General Public License v3.0.

Model language: Persian / Farsi / fa, fa-IR.

Person or organization developing model: Maintained by oct4pie.

Model card for Persian STT v0.1.0 Model details

The acoustic and language models are available in releases.Thankfully, the scorer is able to handle most of these cases, according to the context.For example, the model is unable to distinguish between the following words by themselves: It is worth noting that many of the errors are due to the language syntax.Then, the dropout rate was decreased as the learning rate was decreasing due to the plateau to reach the minimum loss values.

Scorer_path = '/content/kenlm-persian.scorer',

The model was trained with the following configuration:.

Tranfer learning from the STT English model was enabled (with drop_source_layers=2).

Training was stopped at 1896648 steps after optimizing the model.

Learning_rate was increased for the second run from 0.00012 to 0.0004.

The model was trained 2 separate times with force_initialize_learning_rate.

Then, the corpus was normalized, tokenized, and cleaned using the persianify function and _HTMLStripper in the notebook.

The raw text corpus was obtained from here.

The generated validated.csv was passed to auto_input_dataset=metadata in the configuation step.

Using STT's bin/import_cv2.py script, the data was matched to the alphabet converted to CSV files.

The Common-Voice dataset was obtained from here.

#GITHUB PERIAN DAATA HOW TO#

persian_stt.ipynb contains a notebook that demonstrates how to preprocess the data.Approaches to uncertainty and variability.Then you can use below command.This is a Persian DeepSpeech model that is currently in development. You must append your stems to the fourth column. The first column is the inflected word, the second is its stem and the third is its part-of-speech. UsageĮach stemming dataset is consist of three columns. It supports all the metrics of stemming evalution such as Accuracy, Percision, Recall, F-Measure, Understemming and Overstemming Errors, Commission and Ommission Errors. It generates report based on your result. You can use the evaluate.exe in order to evalute your stemming results. These two datasets have good qualities in terms of the diversity of their Part-of-Speech tags. The words and their stems of this dataset have been extracted from the Persian Dependency TreeBank corpus. Moreover, in order to perform a better evaluation, we selected a large text corpus for the second dataset.

This corpus contains 4,689 distinct words. The first dataset contains a collection of words and their stems, which has been extracted from the PerTreeBank corpus. These datasets are automatically extracted from two manually stemmed corpora. In order to create a dataset for correctness evaluation of stemmers, we require a set of words with their stems. There is no standard dataset for correctness evaluation of Persian stemming algorithms. Persian Stemming data-set in order to evaluate new stemmers Description