/
core.html
636 lines (603 loc) · 37.9 KB
/
core.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1" />
<meta name="generator" content="pdoc 0.9.2" />
<title>ktrain.text.translation.core API documentation</title>
<meta name="description" content="" />
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/sanitize.min.css" integrity="sha256-PK9q560IAAa6WVRRh76LtCaI8pjTJ2z11v0miyNNjrs=" crossorigin>
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/typography.min.css" integrity="sha256-7l/o7C8jubJiy74VsKTidCy1yBkRtiUGbVkYBylBqUg=" crossorigin>
<link rel="stylesheet preload" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/styles/github.min.css" crossorigin>
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:30px;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:1em 0 .50em 0}h3{font-size:1.4em;margin:25px 0 10px 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .3s ease-in-out}a:hover{color:#e82}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900}pre code{background:#f8f8f8;font-size:.8em;line-height:1.4em}code{background:#f2f2f1;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{background:#f8f8f8;border:0;border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0;padding:1ex}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-weight:bold;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em .5em;margin-bottom:1em}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.item .name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul{padding-left:1.5em}.toc > ul > li{margin-top:.5em}}</style>
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/highlight.min.js" integrity="sha256-Uv3H6lx7dJmRfRvH8TH6kJD1TSK1aFcwgx+mdg3epi8=" crossorigin></script>
<script>window.addEventListener('DOMContentLoaded', () => hljs.initHighlighting())</script>
</head>
<body>
<main>
<article id="content">
<header>
<h1 class="title">Module <code>ktrain.text.translation.core</code></h1>
</header>
<section id="section-intro">
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">from ...imports import *
from ... import utils as U
from .. import textutils as TU
SUPPORTED_SRC_LANGS = ['zh', 'ar', 'ru', 'de', 'af', 'es', 'fr', 'it', 'pt']
class Translator():
"""
Translator: basic wrapper around MarianMT model for language translation
"""
def __init__(self, model_name=None, device=None, half=False):
"""
```
basic wrapper around MarianMT model for language translation
Args:
model_name(str): Helsinki-NLP model
device(str): device to use (e.g., 'cuda', 'cpu')
half(bool): If True, use half precision.
```
"""
if 'Helsinki-NLP' not in model_name:
warnings.warn('Translator requires a Helsinki-NLP model: https://huggingface.co/Helsinki-NLP')
try:
import torch
except ImportError:
raise Exception('Translator requires PyTorch to be installed.')
self.torch_device = device
if self.torch_device is None: self.torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
from transformers import MarianMTModel, MarianTokenizer
self.tokenizer = MarianTokenizer.from_pretrained(model_name)
self.model = MarianMTModel.from_pretrained(model_name).to(self.torch_device)
if half: self.model = self.model.half()
def translate(self, src_text, join_with='\n', num_beams=None, early_stopping=None):
"""
```
Translate document (src_text).
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
src_text(str): source text.
The source text can either be a single sentence or an entire document with multiple sentences
and paragraphs.
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
join_with(str): list of translated sentences will be delimited with this character.
default: each sentence on separate line
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated text
```
"""
sentences = TU.sent_tokenize(src_text)
tgt_sentences = self.translate_sentences(sentences, num_beams=num_beams, early_stopping=early_stopping)
return join_with.join(tgt_sentences)
def translate_sentences(self, sentences, num_beams=None, early_stopping=None):
"""
```
Translate sentences using model_name as model.
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
sentences(list): list of strings representing sentences that need to be translated
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated sentences
```
"""
import torch
with torch.no_grad():
translated = self.model.generate(**self.tokenizer.prepare_seq2seq_batch(sentences, return_tensors='pt').to(self.torch_device),
num_beams=num_beams, early_stopping=early_stopping)
tgt_sentences = [self.tokenizer.decode(t, skip_special_tokens=True) for t in translated]
return tgt_sentences
class EnglishTranslator():
"""
Class to translate text in various languages to English.
"""
def __init__(self, src_lang=None, device=None):
"""
```
Constructor for English translator
Args:
src_lang(str): language code of source language.
Must be one of SUPPORTED_SRC_LANGS:
'zh': Chinese (either tradtional or simplified)
'ar': Arabic
'ru' : Russian
'de': German
'af': Afrikaans
'es': Spanish
'fr': French
'it': Italian
'pt': Portuguese
device(str): device to use (e.g., 'cuda', 'cpu')
```
"""
if src_lang is None or src_lang not in SUPPORTED_SRC_LANGS:
raise ValueError('A src_lang must be supplied and be one of: %s' % (SUPPORED_SRC_LANG))
self.src_lang = src_lang
self.translators = []
if src_lang == 'ar':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-ar-en', device=device))
elif src_lang == 'ru':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-ru-en', device=device))
elif src_lang == 'de':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-de-en', device=device))
elif src_lang == 'af':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-af-en', device=device))
elif src_lang in ['es', 'fr', 'it', 'pt']:
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-ROMANCE-en', device=device))
#elif src_lang == 'zh': # could not find zh->en model, so currently doing two-step translation to English via German
#self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-ZH-de', device=device))
#self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-de-en', device=device))
elif src_lang == 'zh':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-zh-en', device=device))
else:
raise ValueError('lang:%s is currently not supported.' % (src_lang))
def translate(self, src_text, join_with='\n', num_beams=None, early_stopping=None):
"""
```
Translate source document to English.
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
src_text(str): source text. Must be in language specified by src_lang (language code) supplied to constructor
The source text can either be a single sentence or an entire document with multiple sentences
and paragraphs.
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
join_with(str): list of translated sentences will be delimited with this character.
default: each sentence on separate line
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated text
```
"""
text = src_text
for t in self.translators:
text = t.translate(text, join_with=join_with, num_beams=num_beams, early_stopping=early_stopping)
return text
</code></pre>
</details>
</section>
<section>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-classes">Classes</h2>
<dl>
<dt id="ktrain.text.translation.core.EnglishTranslator"><code class="flex name class">
<span>class <span class="ident">EnglishTranslator</span></span>
<span>(</span><span>src_lang=None, device=None)</span>
</code></dt>
<dd>
<div class="desc"><p>Class to translate text in various languages to English.</p>
<pre><code>Constructor for English translator
Args:
src_lang(str): language code of source language.
Must be one of SUPPORTED_SRC_LANGS:
'zh': Chinese (either tradtional or simplified)
'ar': Arabic
'ru' : Russian
'de': German
'af': Afrikaans
'es': Spanish
'fr': French
'it': Italian
'pt': Portuguese
device(str): device to use (e.g., 'cuda', 'cpu')
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">class EnglishTranslator():
"""
Class to translate text in various languages to English.
"""
def __init__(self, src_lang=None, device=None):
"""
```
Constructor for English translator
Args:
src_lang(str): language code of source language.
Must be one of SUPPORTED_SRC_LANGS:
'zh': Chinese (either tradtional or simplified)
'ar': Arabic
'ru' : Russian
'de': German
'af': Afrikaans
'es': Spanish
'fr': French
'it': Italian
'pt': Portuguese
device(str): device to use (e.g., 'cuda', 'cpu')
```
"""
if src_lang is None or src_lang not in SUPPORTED_SRC_LANGS:
raise ValueError('A src_lang must be supplied and be one of: %s' % (SUPPORED_SRC_LANG))
self.src_lang = src_lang
self.translators = []
if src_lang == 'ar':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-ar-en', device=device))
elif src_lang == 'ru':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-ru-en', device=device))
elif src_lang == 'de':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-de-en', device=device))
elif src_lang == 'af':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-af-en', device=device))
elif src_lang in ['es', 'fr', 'it', 'pt']:
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-ROMANCE-en', device=device))
#elif src_lang == 'zh': # could not find zh->en model, so currently doing two-step translation to English via German
#self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-ZH-de', device=device))
#self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-de-en', device=device))
elif src_lang == 'zh':
self.translators.append(Translator(model_name='Helsinki-NLP/opus-mt-zh-en', device=device))
else:
raise ValueError('lang:%s is currently not supported.' % (src_lang))
def translate(self, src_text, join_with='\n', num_beams=None, early_stopping=None):
"""
```
Translate source document to English.
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
src_text(str): source text. Must be in language specified by src_lang (language code) supplied to constructor
The source text can either be a single sentence or an entire document with multiple sentences
and paragraphs.
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
join_with(str): list of translated sentences will be delimited with this character.
default: each sentence on separate line
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated text
```
"""
text = src_text
for t in self.translators:
text = t.translate(text, join_with=join_with, num_beams=num_beams, early_stopping=early_stopping)
return text</code></pre>
</details>
<h3>Methods</h3>
<dl>
<dt id="ktrain.text.translation.core.EnglishTranslator.translate"><code class="name flex">
<span>def <span class="ident">translate</span></span>(<span>self, src_text, join_with='\n', num_beams=None, early_stopping=None)</span>
</code></dt>
<dd>
<div class="desc"><pre><code>Translate source document to English.
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
src_text(str): source text. Must be in language specified by src_lang (language code) supplied to constructor
The source text can either be a single sentence or an entire document with multiple sentences
and paragraphs.
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
join_with(str): list of translated sentences will be delimited with this character.
default: each sentence on separate line
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated text
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def translate(self, src_text, join_with='\n', num_beams=None, early_stopping=None):
"""
```
Translate source document to English.
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
src_text(str): source text. Must be in language specified by src_lang (language code) supplied to constructor
The source text can either be a single sentence or an entire document with multiple sentences
and paragraphs.
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
join_with(str): list of translated sentences will be delimited with this character.
default: each sentence on separate line
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated text
```
"""
text = src_text
for t in self.translators:
text = t.translate(text, join_with=join_with, num_beams=num_beams, early_stopping=early_stopping)
return text</code></pre>
</details>
</dd>
</dl>
</dd>
<dt id="ktrain.text.translation.core.Translator"><code class="flex name class">
<span>class <span class="ident">Translator</span></span>
<span>(</span><span>model_name=None, device=None, half=False)</span>
</code></dt>
<dd>
<div class="desc"><p>Translator: basic wrapper around MarianMT model for language translation</p>
<pre><code>basic wrapper around MarianMT model for language translation
Args:
model_name(str): Helsinki-NLP model
device(str): device to use (e.g., 'cuda', 'cpu')
half(bool): If True, use half precision.
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">class Translator():
"""
Translator: basic wrapper around MarianMT model for language translation
"""
def __init__(self, model_name=None, device=None, half=False):
"""
```
basic wrapper around MarianMT model for language translation
Args:
model_name(str): Helsinki-NLP model
device(str): device to use (e.g., 'cuda', 'cpu')
half(bool): If True, use half precision.
```
"""
if 'Helsinki-NLP' not in model_name:
warnings.warn('Translator requires a Helsinki-NLP model: https://huggingface.co/Helsinki-NLP')
try:
import torch
except ImportError:
raise Exception('Translator requires PyTorch to be installed.')
self.torch_device = device
if self.torch_device is None: self.torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
from transformers import MarianMTModel, MarianTokenizer
self.tokenizer = MarianTokenizer.from_pretrained(model_name)
self.model = MarianMTModel.from_pretrained(model_name).to(self.torch_device)
if half: self.model = self.model.half()
def translate(self, src_text, join_with='\n', num_beams=None, early_stopping=None):
"""
```
Translate document (src_text).
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
src_text(str): source text.
The source text can either be a single sentence or an entire document with multiple sentences
and paragraphs.
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
join_with(str): list of translated sentences will be delimited with this character.
default: each sentence on separate line
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated text
```
"""
sentences = TU.sent_tokenize(src_text)
tgt_sentences = self.translate_sentences(sentences, num_beams=num_beams, early_stopping=early_stopping)
return join_with.join(tgt_sentences)
def translate_sentences(self, sentences, num_beams=None, early_stopping=None):
"""
```
Translate sentences using model_name as model.
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
sentences(list): list of strings representing sentences that need to be translated
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated sentences
```
"""
import torch
with torch.no_grad():
translated = self.model.generate(**self.tokenizer.prepare_seq2seq_batch(sentences, return_tensors='pt').to(self.torch_device),
num_beams=num_beams, early_stopping=early_stopping)
tgt_sentences = [self.tokenizer.decode(t, skip_special_tokens=True) for t in translated]
return tgt_sentences</code></pre>
</details>
<h3>Methods</h3>
<dl>
<dt id="ktrain.text.translation.core.Translator.translate"><code class="name flex">
<span>def <span class="ident">translate</span></span>(<span>self, src_text, join_with='\n', num_beams=None, early_stopping=None)</span>
</code></dt>
<dd>
<div class="desc"><pre><code>Translate document (src_text).
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
src_text(str): source text.
The source text can either be a single sentence or an entire document with multiple sentences
and paragraphs.
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
join_with(str): list of translated sentences will be delimited with this character.
default: each sentence on separate line
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated text
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def translate(self, src_text, join_with='\n', num_beams=None, early_stopping=None):
"""
```
Translate document (src_text).
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
src_text(str): source text.
The source text can either be a single sentence or an entire document with multiple sentences
and paragraphs.
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
join_with(str): list of translated sentences will be delimited with this character.
default: each sentence on separate line
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated text
```
"""
sentences = TU.sent_tokenize(src_text)
tgt_sentences = self.translate_sentences(sentences, num_beams=num_beams, early_stopping=early_stopping)
return join_with.join(tgt_sentences)</code></pre>
</details>
</dd>
<dt id="ktrain.text.translation.core.Translator.translate_sentences"><code class="name flex">
<span>def <span class="ident">translate_sentences</span></span>(<span>self, sentences, num_beams=None, early_stopping=None)</span>
</code></dt>
<dd>
<div class="desc"><pre><code>Translate sentences using model_name as model.
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
sentences(list): list of strings representing sentences that need to be translated
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated sentences
</code></pre></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def translate_sentences(self, sentences, num_beams=None, early_stopping=None):
"""
```
Translate sentences using model_name as model.
To speed up translations, you can set num_beams and early_stopping (e.g., num_beams=4, early_stopping=True).
Args:
sentences(list): list of strings representing sentences that need to be translated
IMPORTANT NOTE: Sentences are joined together and fed to model as single batch.
If the input text is very large (e.g., an entire book), you should
break it up into reasonbly-sized chunks (e.g., pages, paragraphs, or sentences) and
feed each chunk separately into translate to avoid out-of-memory issues.
num_beams(int): Number of beams for beam search. Defaults to None. If None, the transformers library defaults this to 1,
whicn means no beam search.
early_stopping(bool): Whether to stop the beam search when at least ``num_beams`` sentences
are finished per batch or not. Defaults to None. If None, the transformers library
sets this to False.
Returns:
str: translated sentences
```
"""
import torch
with torch.no_grad():
translated = self.model.generate(**self.tokenizer.prepare_seq2seq_batch(sentences, return_tensors='pt').to(self.torch_device),
num_beams=num_beams, early_stopping=early_stopping)
tgt_sentences = [self.tokenizer.decode(t, skip_special_tokens=True) for t in translated]
return tgt_sentences</code></pre>
</details>
</dd>
</dl>
</dd>
</dl>
</section>
</article>
<nav id="sidebar">
<h1>Index</h1>
<div class="toc">
<ul></ul>
</div>
<ul id="index">
<li><h3>Super-module</h3>
<ul>
<li><code><a title="ktrain.text.translation" href="index.html">ktrain.text.translation</a></code></li>
</ul>
</li>
<li><h3><a href="#header-classes">Classes</a></h3>
<ul>
<li>
<h4><code><a title="ktrain.text.translation.core.EnglishTranslator" href="#ktrain.text.translation.core.EnglishTranslator">EnglishTranslator</a></code></h4>
<ul class="">
<li><code><a title="ktrain.text.translation.core.EnglishTranslator.translate" href="#ktrain.text.translation.core.EnglishTranslator.translate">translate</a></code></li>
</ul>
</li>
<li>
<h4><code><a title="ktrain.text.translation.core.Translator" href="#ktrain.text.translation.core.Translator">Translator</a></code></h4>
<ul class="">
<li><code><a title="ktrain.text.translation.core.Translator.translate" href="#ktrain.text.translation.core.Translator.translate">translate</a></code></li>
<li><code><a title="ktrain.text.translation.core.Translator.translate_sentences" href="#ktrain.text.translation.core.Translator.translate_sentences">translate_sentences</a></code></li>
</ul>
</li>
</ul>
</li>
</ul>
</nav>
</main>
<footer id="footer">
<p>Generated by <a href="https://pdoc3.github.io/pdoc"><cite>pdoc</cite> 0.9.2</a>.</p>
</footer>
</body>
</html>