vietai / mtet Goto Github PK

Hi team @lmthang @thtrieu @heraclex12 @hqphat @KienHuynh

The obtained results of a Transformer-based model on the PhoMT test set surprised me. My first thought was that as VietAI and PhoMT datasets have several overlapping domains (e.g. Wikihow, TED talks, Opensubtitles, news..): whether there might be a potential data leakage issue in your evaluation (e.g. PhoMT English-Vietnamese test pairs appear in the VietAI training set)?

In particular, we find that 6294/19151 PhoMT English-Vietnamese test pairs appear in the VietAI training set (v2). When evaluating your model on the PhoMT test set, did you guys retrain the model on a VietAI training set variant that does not contain PhoMT English-Vietnamese test pairs?

Cheers,
Dat.

I ran the Readme.md samples on Google Colab with GPU and got this Error "RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper__index_select)".

Error code:
outputs = model.generate(tokenizer(inputs, return_tensors="pt", padding=True).input_ids.to('cuda'), max_length=512)

I followed your notebook and got the following error.

python3: can't open file '/content/sat/t2t_datagen.py': [Errno 2] No such file or directory

Hello,

Since v2 dataset files have not yet been available at the moment, I'm wondering where can I get download the v1 dataset files? It seems that all files within the GCS bucket cannot be downloaded (I get 403 forbidden every time).

Thank you and best regards.

Tôi không tải về được (Forbiden). Vui lòng giúp tôi.

Cám ơn.
Nguyên ([email protected])

I have tried the example on my Macbook M1 pro but got this error:
=>outputs = model.generate(tokenizer(inputs, return_tensors="pt", padding=True).input_ids.to('cuda'), max_length=512)
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

Please help!

When i use model to translate Eng-Vie, the model has converted units like pounds, feet, to kilograms, meter. But i don't want to convert those units. How can I use the model without converting those units?

Data loss: Unable to open table file /content/drive/MyDrive/SAT/checkpoint: Failed precondition: /content/drive/MyDrive/SAT/checkpoint; Is a directory: perhaps your file is in a different file format and you need to use a different restore operator?

I used a pretrain model : model.augmented.envi.ckpt-1415000.data-00000-of-00001, model.augmented.envi.ckpt-1415000.index, model.augmented.envi.ckpt-1415000.meta. All 3 file are put in checkpoint

Could somebody help me with this issue ?

I have a question about loading model. I have trained a Russian-to-Vietnamese model base on your code and tensor2tensor. Every time I want to predict a new sentence, it always load the model again, even before that I have already predicted another sentence. I want to ask that if there is a way not to have reload the model when predict a new sentence. Thank you very much

I just download mTet-v2 via an HF dataset link provided in this comment which contains 4.19M training pairs. However, I find that 9.9K mTet-v2 training pairs appear in the PhoMT test set.

Please assist in correcting this mTet-v2 dataset for a proper evaluation. Thank you!

P.S.: You can find the English training sentences in mTet-v2 that appear in the PhoMT test set in the attached file: mtet-training-pairs-in-phomt-test-set.en.txt

Hi VietAI team,

I want to express my gratitude for publishing the 2nd version of the mTet dataset, V1.0 and V2.0. I followed the provided instructions for downloading the dataset from the shared file. However, I encountered an issue when using the source code provided on GitHub to extract the dataset into the tfrecord format.

Steps Taken:

• Original command used for generating tfrecords from raw text files:

python t2t_datagen.py
--data_dir=$path_to_folder_contains_vocab_file
--tmp_dir=$path_to_folder_that_contains_training_data
--problem=$problem

Environment Setting:

• Tensorflow version: 1.15
• Tensor2tensor version: 1.13.3

Issue Details:
The output of the provided code only downloads the EnviIwslt32k dataset and converts it to a readable format and tfrecord files. However, the two data files from the mTet dataset (highlighted in the attached image) are not being extracted.

Authors have any suggestions or updates on how to successfully extract these datasets?. Thank you so much for your assistance and your valuable contributions.

I haven't find v2 training data in the link provided

Hi,
seems like the easiest to reach out here but https://demo.vietai.org/ is down, looks like the page tried to serve a 404 error page.

Connection failed with status 404, and response "<!DOCTYPE html> <html lang=en> <meta charset=utf-8> <meta name=viewport content="initial-scale=1, minimum-scale=1, width=device-width"> <title>Error 404 (Not Found)!!1</title> <style> *{margin:0;padding:0}html,code{font:15px/22px arial,sans-serif}html{background:#fff;color:#222;padding:15px}body{margin:7% auto 0;max-width:390px;min-height:180px;padding:30px 0 15px}* > body{background:url(//www.google.com/images/errors/robot.png) 100% 5px no-repeat;padding-right:205px}p{margin:11px 0 22px;overflow:hidden}ins{color:#777;text-decoration:none}a img{border:0}@media screen and (max-width:772px){body{background:none;margin-top:0;max-width:none;padding-right:0}}#logo{background:url(//www.google.com/images/branding/googlelogo/1x/googlelogo_color_150x54dp.png) no-repeat;margin-left:-5px}@media only screen and (min-resolution:192dpi){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat 0% 0%/100% 100%;-moz-border-image:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) 0}}@media only screen and (-webkit-min-device-pixel-ratio:2){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat;-webkit-background-size:100% 100%}}#logo{display:inline-block;height:54px;width:150px} </style> <a href=//www.google.com/><span id=logo aria-label=Google></span></a> <p><b>404.</b> <ins>That’s an error.</ins> <p>The requested URL <code>/healthz</code> was not found on this server. <ins>That’s all we know.</ins> ".