Issues
- 1
do it support qwen model?
#277 opened by xxm1668 - 3
How can I parallelize LASER embeddings?
#278 opened by prasunshrestha - 1
Similarity calculation takes too long with LASER3 model, compared to XLM-R/LaBSE
#281 opened by aloka-fernando - 1
- 10
Unable to import LaserEncoderPipeline
#280 opened by sumedhan-r - 1
Can't download: 403 error on some CC segments.
#279 opened by enn-nafnlaus - 1
Create a tutorial showing how LASER can be applied for downstream practical tasks (e.g. multilingual sentiment analysis)
#271 opened by avidale - 1
- 2
The included Dockerfile and associated Flask app is out of date in multiple ways.
#245 opened by andy-weinstein - 4
- 0
- 1
Make LASER pip-installable
#235 opened by avidale - 1
Port LASER-2,3 text preprocessing into Python
#236 opened by avidale - 1
Python interface for downloading and choosing models
#237 opened by avidale - 0
Reorganize the lists of languages
#267 opened by avidale - 0
Publish the performance of LASER2 and LASER3 encoders on each of the FLORES-200 languages
#270 opened by avidale - 0
Try decreasing the minimal versions of numpy and torch required by laser-encoders
#263 opened by avidale - 0
- 0
- 0
Suggestion: add normalization option in the
#261 opened by avidale - 2
SPM models not available
#250 opened by tbst730 - 2
- 2
- 1
- 3
LASER2 vocab contains upper case characters
#220 opened by ZJaume - 1
embed_sentences Path parameters
#231 opened by julianpollmann - 3
CCMatrix Data download
#233 opened by yangyang0202 - 1
Clarification for Chinese language variants
#225 opened by raunaksinhacisco - 3
- 3
Laser v2, set Language to compute Embeddings on
#234 opened by celcof - 9
spm_encode: No such file or directory
#222 opened by zzzul9 - 2
- 2
Laser support for non-official data
#223 opened by joshdehlong - 2
Text preprocessing before embedding
#226 opened by mrkcdl - 2
Is there a limit of sentence length for LASER?
#227 opened by maohbao - 8
Using LASER 2 and LASER 3 to filter good quality sentence pairs from a webcrawled parallel dataset
#229 opened by vmenan - 4
Problem with wet_lines
#228 opened by vmenan - 2
how to get the sentence embedding using Librivox S2S?
#224 opened by zhhao1 - 2
Sentence Embedding Reads No Input
#221 opened by prasunshrestha - 2
- 5
Embedding tasks stop at pre-processing phase.
#215 opened by Vietdung113 - 4
- 38
when run bash ./eval.sh & python eval.py & Call functions embed_sentences show error // spm_encode:No such file or directory
#212 opened by dcmouth - 2
embed task stops at preprocessing
#213 opened by ruoyuxie - 3
.enc and .candidates.tsv
#209 opened by guangyuli-uoe - 7
cannot install fastbpe
#205 opened by guangyuli-uoe - 3
cannot install sentence-transformers
#208 opened by guangyuli-uoe - 10
embed models
#211 opened by guangyuli-uoe - 1
Segmentation fault
#210 opened by guangyuli-uoe - 1