Spaces:
Runtime error
Runtime error
José Ángel González
commited on
Commit
·
f40bceb
1
Parent(s):
c5c47e6
Revert "revert to gpu"
Browse filesThis reverts commit c5c47e65a17c658e2a67eb41dba237613aa0b28f.
__pycache__/app.cpython-310.pyc
DELETED
|
Binary file (307 Bytes)
|
|
|
__pycache__/gradio_tst.cpython-310.pyc
DELETED
|
Binary file (4.49 kB)
|
|
|
generation_evaluator.py
CHANGED
|
@@ -62,7 +62,7 @@ Note that ROUGE is case insensitive, meaning that upper case letters are treated
|
|
| 62 |
This metrics is a wrapper around Google Research reimplementation of ROUGE:
|
| 63 |
https://github.com/google-research/google-research/tree/master/rouge
|
| 64 |
|
| 65 |
-
|
| 66 |
Quality is considered to be the correspondence between a machine's output and that of a human: "the closer a machine translation is to a professional human translation, the better it is"
|
| 67 |
this is the central idea behind BLEU. BLEU was one of the first metrics to claim a high correlation with human judgements of quality, and remains one of the most popular automated and inexpensive metrics.
|
| 68 |
|
|
@@ -133,7 +133,7 @@ CHRF:{
|
|
| 133 |
ALIGNSCORE_ARGS = {
|
| 134 |
"model": "roberta-base",
|
| 135 |
"batch_size": 32,
|
| 136 |
-
"device": "
|
| 137 |
"ckpt_path": "https://huggingface.co/yzha/AlignScore/resolve/main/AlignScore-base.ckpt",
|
| 138 |
"evaluation_mode": "nli_sp",
|
| 139 |
}
|
|
|
|
| 62 |
This metrics is a wrapper around Google Research reimplementation of ROUGE:
|
| 63 |
https://github.com/google-research/google-research/tree/master/rouge
|
| 64 |
|
| 65 |
+
BLEU (Bilingual Evaluation Understudy) is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another.
|
| 66 |
Quality is considered to be the correspondence between a machine's output and that of a human: "the closer a machine translation is to a professional human translation, the better it is"
|
| 67 |
this is the central idea behind BLEU. BLEU was one of the first metrics to claim a high correlation with human judgements of quality, and remains one of the most popular automated and inexpensive metrics.
|
| 68 |
|
|
|
|
| 133 |
ALIGNSCORE_ARGS = {
|
| 134 |
"model": "roberta-base",
|
| 135 |
"batch_size": 32,
|
| 136 |
+
"device": "cpu",
|
| 137 |
"ckpt_path": "https://huggingface.co/yzha/AlignScore/resolve/main/AlignScore-base.ckpt",
|
| 138 |
"evaluation_mode": "nli_sp",
|
| 139 |
}
|