File size: 17,396 Bytes
ee21b96
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#!/usr/bin/env python3

# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

"""
Flashlight decoders.
"""

import gc
import itertools as it
import os.path as osp
from typing import List
import warnings
from collections import deque, namedtuple

import numpy as np
import torch
from examples.speech_recognition.data.replabels import unpack_replabels
from fairseq import tasks
from fairseq.utils import apply_to_sample
from omegaconf import open_dict
from fairseq.dataclass.utils import convert_namespace_to_omegaconf


try:
    from flashlight.lib.text.dictionary import create_word_dict, load_words
    from flashlight.lib.sequence.criterion import CpuViterbiPath, get_data_ptr_as_bytes
    from flashlight.lib.text.decoder import (
        CriterionType,
        LexiconDecoderOptions,
        KenLM,
        LM,
        LMState,
        SmearingMode,
        Trie,
        LexiconDecoder,
    )
except:
    warnings.warn(
        "flashlight python bindings are required to use this functionality. Please install from https://github.com/facebookresearch/flashlight/tree/master/bindings/python"
    )
    LM = object
    LMState = object


class W2lDecoder(object):
    def __init__(self, args, tgt_dict):
        self.tgt_dict = tgt_dict
        self.vocab_size = len(tgt_dict)
        self.nbest = args.nbest

        # criterion-specific init
        self.criterion_type = CriterionType.CTC
        self.blank = (
            tgt_dict.index("<ctc_blank>")
            if "<ctc_blank>" in tgt_dict.indices
            else tgt_dict.bos()
        )
        if "<sep>" in tgt_dict.indices:
            self.silence = tgt_dict.index("<sep>")
        elif "|" in tgt_dict.indices:
            self.silence = tgt_dict.index("|")
        else:
            self.silence = tgt_dict.eos()
        self.asg_transitions = None

    def generate(self, models, sample, **unused):
        """Generate a batch of inferences."""
        # model.forward normally channels prev_output_tokens into the decoder
        # separately, but SequenceGenerator directly calls model.encoder
        encoder_input = {
            k: v for k, v in sample["net_input"].items() if k != "prev_output_tokens"
        }
        emissions = self.get_emissions(models, encoder_input)
        return self.decode(emissions)

    def get_emissions(self, models, encoder_input):
        """Run encoder and normalize emissions"""
        model = models[0]
        encoder_out = model(**encoder_input)
        if hasattr(model, "get_logits"):
            emissions = model.get_logits(encoder_out) # no need to normalize emissions
        else:
            emissions = model.get_normalized_probs(encoder_out, log_probs=True)
        return emissions.transpose(0, 1).float().cpu().contiguous()

    def get_tokens(self, idxs):
        """Normalize tokens by handling CTC blank, ASG replabels, etc."""
        idxs = (g[0] for g in it.groupby(idxs))
        idxs = filter(lambda x: x != self.blank, idxs)
        return torch.LongTensor(list(idxs))


class W2lViterbiDecoder(W2lDecoder):
    def __init__(self, args, tgt_dict):
        super().__init__(args, tgt_dict)

    def decode(self, emissions):
        B, T, N = emissions.size()
        hypos = []
        if self.asg_transitions is None:
            transitions = torch.FloatTensor(N, N).zero_()
        else:
            transitions = torch.FloatTensor(self.asg_transitions).view(N, N)
        viterbi_path = torch.IntTensor(B, T)
        workspace = torch.ByteTensor(CpuViterbiPath.get_workspace_size(B, T, N))
        CpuViterbiPath.compute(
            B,
            T,
            N,
            get_data_ptr_as_bytes(emissions),
            get_data_ptr_as_bytes(transitions),
            get_data_ptr_as_bytes(viterbi_path),
            get_data_ptr_as_bytes(workspace),
        )
        return [
            [{"tokens": self.get_tokens(viterbi_path[b].tolist()), "score": 0}]
            for b in range(B)
        ]


class W2lKenLMDecoder(W2lDecoder):
    def __init__(self, args, tgt_dict):
        super().__init__(args, tgt_dict)

        self.unit_lm = getattr(args, "unit_lm", False)

        if args.lexicon:
            self.lexicon = load_words(args.lexicon)
            self.word_dict = create_word_dict(self.lexicon)
            self.unk_word = self.word_dict.get_index("<unk>")

            self.lm = KenLM(args.kenlm_model, self.word_dict)
            self.trie = Trie(self.vocab_size, self.silence)

            start_state = self.lm.start(False)
            for i, (word, spellings) in enumerate(self.lexicon.items()):
                word_idx = self.word_dict.get_index(word)
                _, score = self.lm.score(start_state, word_idx)
                for spelling in spellings:
                    spelling_idxs = [tgt_dict.index(token) for token in spelling]
                    assert (
                        tgt_dict.unk() not in spelling_idxs
                    ), f"{spelling} {spelling_idxs}"
                    self.trie.insert(spelling_idxs, word_idx, score)
            self.trie.smear(SmearingMode.MAX)

            self.decoder_opts = LexiconDecoderOptions(
                beam_size=args.beam,
                beam_size_token=int(getattr(args, "beam_size_token", len(tgt_dict))),
                beam_threshold=args.beam_threshold,
                lm_weight=args.lm_weight,
                word_score=args.word_score,
                unk_score=args.unk_weight,
                sil_score=args.sil_weight,
                log_add=False,
                criterion_type=self.criterion_type,
            )

            if self.asg_transitions is None:
                N = 768
                # self.asg_transitions = torch.FloatTensor(N, N).zero_()
                self.asg_transitions = []

            self.decoder = LexiconDecoder(
                self.decoder_opts,
                self.trie,
                self.lm,
                self.silence,
                self.blank,
                self.unk_word,
                self.asg_transitions,
                self.unit_lm,
            )
        else:
            assert args.unit_lm, "lexicon free decoding can only be done with a unit language model"
            from flashlight.lib.text.decoder import LexiconFreeDecoder, LexiconFreeDecoderOptions

            d = {w: [[w]] for w in tgt_dict.symbols}
            self.word_dict = create_word_dict(d)
            self.lm = KenLM(args.kenlm_model, self.word_dict)
            self.decoder_opts = LexiconFreeDecoderOptions(
                beam_size=args.beam,
                beam_size_token=int(getattr(args, "beam_size_token", len(tgt_dict))),
                beam_threshold=args.beam_threshold,
                lm_weight=args.lm_weight,
                sil_score=args.sil_weight,
                log_add=False,
                criterion_type=self.criterion_type,
            )
            self.decoder = LexiconFreeDecoder(
                self.decoder_opts, self.lm, self.silence, self.blank, []
            )

    def get_timesteps(self, token_idxs: List[int]) -> List[int]:
        """Returns frame numbers corresponding to every non-blank token.

        Parameters
        ----------
        token_idxs : List[int]
            IDs of decoded tokens.

        Returns
        -------
        List[int]
            Frame numbers corresponding to every non-blank token.
        """
        timesteps = []
        for i, token_idx in enumerate(token_idxs):
            if token_idx == self.blank:
                continue
            if i == 0 or token_idx != token_idxs[i-1]:
                timesteps.append(i)
        return timesteps

    def decode(self, emissions):
        B, T, N = emissions.size()
        hypos = []
        for b in range(B):
            emissions_ptr = emissions.data_ptr() + 4 * b * emissions.stride(0)
            results = self.decoder.decode(emissions_ptr, T, N)

            nbest_results = results[: self.nbest]
            hypos.append(
                [
                    {
                        "tokens": self.get_tokens(result.tokens),
                        "score": result.score,
                        "timesteps": self.get_timesteps(result.tokens),
                        "words": [
                            self.word_dict.get_entry(x) for x in result.words if x >= 0
                        ],
                    }
                    for result in nbest_results
                ]
            )
        return hypos


FairseqLMState = namedtuple("FairseqLMState", ["prefix", "incremental_state", "probs"])


class FairseqLM(LM):
    def __init__(self, dictionary, model):
        LM.__init__(self)
        self.dictionary = dictionary
        self.model = model
        self.unk = self.dictionary.unk()

        self.save_incremental = False  # this currently does not work properly
        self.max_cache = 20_000

        model.cuda()
        model.eval()
        model.make_generation_fast_()

        self.states = {}
        self.stateq = deque()

    def start(self, start_with_nothing):
        state = LMState()
        prefix = torch.LongTensor([[self.dictionary.eos()]])
        incremental_state = {} if self.save_incremental else None
        with torch.no_grad():
            res = self.model(prefix.cuda(), incremental_state=incremental_state)
            probs = self.model.get_normalized_probs(res, log_probs=True, sample=None)

        if incremental_state is not None:
            incremental_state = apply_to_sample(lambda x: x.cpu(), incremental_state)
        self.states[state] = FairseqLMState(
            prefix.numpy(), incremental_state, probs[0, -1].cpu().numpy()
        )
        self.stateq.append(state)

        return state

    def score(self, state: LMState, token_index: int, no_cache: bool = False):
        """
        Evaluate language model based on the current lm state and new word
        Parameters:
        -----------
        state: current lm state
        token_index: index of the word
                     (can be lexicon index then you should store inside LM the
                      mapping between indices of lexicon and lm, or lm index of a word)

        Returns:
        --------
        (LMState, float): pair of (new state, score for the current word)
        """
        curr_state = self.states[state]

        def trim_cache(targ_size):
            while len(self.stateq) > targ_size:
                rem_k = self.stateq.popleft()
                rem_st = self.states[rem_k]
                rem_st = FairseqLMState(rem_st.prefix, None, None)
                self.states[rem_k] = rem_st

        if curr_state.probs is None:
            new_incremental_state = (
                curr_state.incremental_state.copy()
                if curr_state.incremental_state is not None
                else None
            )
            with torch.no_grad():
                if new_incremental_state is not None:
                    new_incremental_state = apply_to_sample(
                        lambda x: x.cuda(), new_incremental_state
                    )
                elif self.save_incremental:
                    new_incremental_state = {}

                res = self.model(
                    torch.from_numpy(curr_state.prefix).cuda(),
                    incremental_state=new_incremental_state,
                )
                probs = self.model.get_normalized_probs(
                    res, log_probs=True, sample=None
                )

                if new_incremental_state is not None:
                    new_incremental_state = apply_to_sample(
                        lambda x: x.cpu(), new_incremental_state
                    )

                curr_state = FairseqLMState(
                    curr_state.prefix, new_incremental_state, probs[0, -1].cpu().numpy()
                )

            if not no_cache:
                self.states[state] = curr_state
                self.stateq.append(state)

        score = curr_state.probs[token_index].item()

        trim_cache(self.max_cache)

        outstate = state.child(token_index)
        if outstate not in self.states and not no_cache:
            prefix = np.concatenate(
                [curr_state.prefix, torch.LongTensor([[token_index]])], -1
            )
            incr_state = curr_state.incremental_state

            self.states[outstate] = FairseqLMState(prefix, incr_state, None)

        if token_index == self.unk:
            score = float("-inf")

        return outstate, score

    def finish(self, state: LMState):
        """
        Evaluate eos for language model based on the current lm state

        Returns:
        --------
        (LMState, float): pair of (new state, score for the current word)
        """
        return self.score(state, self.dictionary.eos())

    def empty_cache(self):
        self.states = {}
        self.stateq = deque()
        gc.collect()


class W2lFairseqLMDecoder(W2lDecoder):
    def __init__(self, args, tgt_dict):
        super().__init__(args, tgt_dict)

        self.unit_lm = getattr(args, "unit_lm", False)

        self.lexicon = load_words(args.lexicon) if args.lexicon else None
        self.idx_to_wrd = {}

        checkpoint = torch.load(args.kenlm_model, map_location="cpu")

        if "cfg" in checkpoint and checkpoint["cfg"] is not None:
            lm_args = checkpoint["cfg"]
        else:
            lm_args = convert_namespace_to_omegaconf(checkpoint["args"])

        with open_dict(lm_args.task):
            lm_args.task.data = osp.dirname(args.kenlm_model)

        task = tasks.setup_task(lm_args.task)
        model = task.build_model(lm_args.model)
        model.load_state_dict(checkpoint["model"], strict=False)

        self.trie = Trie(self.vocab_size, self.silence)

        self.word_dict = task.dictionary
        self.unk_word = self.word_dict.unk()
        self.lm = FairseqLM(self.word_dict, model)

        if self.lexicon:
            start_state = self.lm.start(False)
            for i, (word, spellings) in enumerate(self.lexicon.items()):
                if self.unit_lm:
                    word_idx = i
                    self.idx_to_wrd[i] = word
                    score = 0
                else:
                    word_idx = self.word_dict.index(word)
                    _, score = self.lm.score(start_state, word_idx, no_cache=True)

                for spelling in spellings:
                    spelling_idxs = [tgt_dict.index(token) for token in spelling]
                    assert (
                        tgt_dict.unk() not in spelling_idxs
                    ), f"{spelling} {spelling_idxs}"
                    self.trie.insert(spelling_idxs, word_idx, score)
            self.trie.smear(SmearingMode.MAX)

            self.decoder_opts = LexiconDecoderOptions(
                beam_size=args.beam,
                beam_size_token=int(getattr(args, "beam_size_token", len(tgt_dict))),
                beam_threshold=args.beam_threshold,
                lm_weight=args.lm_weight,
                word_score=args.word_score,
                unk_score=args.unk_weight,
                sil_score=args.sil_weight,
                log_add=False,
                criterion_type=self.criterion_type,
            )

            self.decoder = LexiconDecoder(
                self.decoder_opts,
                self.trie,
                self.lm,
                self.silence,
                self.blank,
                self.unk_word,
                [],
                self.unit_lm,
            )
        else:
            assert args.unit_lm, "lexicon free decoding can only be done with a unit language model"
            from flashlight.lib.text.decoder import LexiconFreeDecoder, LexiconFreeDecoderOptions

            d = {w: [[w]] for w in tgt_dict.symbols}
            self.word_dict = create_word_dict(d)
            self.lm = KenLM(args.kenlm_model, self.word_dict)
            self.decoder_opts = LexiconFreeDecoderOptions(
                beam_size=args.beam,
                beam_size_token=int(getattr(args, "beam_size_token", len(tgt_dict))),
                beam_threshold=args.beam_threshold,
                lm_weight=args.lm_weight,
                sil_score=args.sil_weight,
                log_add=False,
                criterion_type=self.criterion_type,
            )
            self.decoder = LexiconFreeDecoder(
                self.decoder_opts, self.lm, self.silence, self.blank, []
            )

    def decode(self, emissions):
        B, T, N = emissions.size()
        hypos = []

        def idx_to_word(idx):
            if self.unit_lm:
                return self.idx_to_wrd[idx]
            else:
                return self.word_dict[idx]

        def make_hypo(result):
            hypo = {"tokens": self.get_tokens(result.tokens), "score": result.score}
            if self.lexicon:
                hypo["words"] = [idx_to_word(x) for x in result.words if x >= 0]
            return hypo

        for b in range(B):
            emissions_ptr = emissions.data_ptr() + 4 * b * emissions.stride(0)
            results = self.decoder.decode(emissions_ptr, T, N)

            nbest_results = results[: self.nbest]
            hypos.append([make_hypo(result) for result in nbest_results])
            self.lm.empty_cache()

        return hypos