bivNSSKJr SSKrSSKJr SSKJr SSKJ r J r J r J r J r Jr SSKrSSKJrJrJrJrJrJrJrJr J!r"J#r$ SSK%J&r'J(r)J*r+ SSK,J-r- SS K.J/r0 /S Qr2\"S /S Q5r3S r4Sr5"SS\ 5r6"SS\5r7"SS\5r8"SS5r9SSSSSSSS\:"S5SSSSS4S"Sjjr;S#S jr_get_word_dictrLAsI( 9$%g.  *tBx3MRS^SiSiSkMl mMl " "1 %)>)>q)A(B'C CMl m zl %a(  ns,B cH\rSrSr%SrS\S'S\S'S\S'S \S 'S rg ) rPzORepresents hypothesis generated by CTC beam search decoder :class:`CTCDecoder`.torch.LongTensorr$z List[str]wordsfloatr,torch.IntTensor timestepsN)__name__ __module__ __qualname____firstlineno____doc____annotations____static_attributes__rTr>rrPs,Z h  L+nr\rcT^\rSrSrSr\SU4Sjj5rSU4SjjrS SjrSr U=r $) rezLanguage model state.c>[TU]$)zMap of indices to LM states)superchildren)self __class__s r>raCTCDecoderLMState.childrenhswr\c">[TU]U5$)zReturns child corresponding to usr_index, or creates and returns a new state if input index is not found. Args: usr_index (int): index corresponding to child state Returns: CTCDecoderLMState: child state corresponding to usr_index )r`child)rb usr_indexrcs r>rfCTCDecoderLMState.childmsw}Y''r\cg)zCompare two language model states. Args: state (CTCDecoderLMState): LM state to compare against Returns: int: 0 if the states are the same, -1 if self is less, +1 if self is greater. NrTrbstates r>compareCTCDecoderLMState.compareys r\rT)returnzDict[int, CTCDecoderLMState])rgintrnr)rkrrnr) rUrVrWrXrYpropertyrarfrlr[ __classcell__)rcs@r>rres'    (   r\rcT\rSrSrSr\SSj5r\S Sj5r\S Sj5rSr g) rzVLanguage model base class for creating custom language models to use with the decoder.c[e)zInitialize or reset the language model. Args: start_with_nothing (bool): whether or not to start sentence with sil token. Returns: CTCDecoderLMState: starting state NotImplementedError)rbstart_with_nothings r>r)CTCDecoderLM.starts "!r\c[e)a(Evaluate the language model based on the current LM state and new word. Args: state (CTCDecoderLMState): current LM state usr_token_idx (int): index of the word Returns: (CTCDecoderLMState, float) CTCDecoderLMState: new LM state float: score ru)rbrk usr_token_idxs r>r,CTCDecoderLM.scores "!r\c[e)zEvaluate end for language model based on current LM state. Args: state (CTCDecoderLMState): current LM state Returns: (CTCDecoderLMState, float) CTCDecoderLMState: new LM state float: score rurjs r>finishCTCDecoderLM.finishs "!r\rTN)rwboolrnr)rkrrzrornTuple[CTCDecoderLMState, float])rkrrnr) rUrVrWrXrYrr)r,r}r[rTr\r>rrs?` " """  " "r\rc\rSrSrSrSSjrSSjrSSjrSrSr SSjr SS jr SS jr SSS jjr SS jrSrg )rzCTC beam search decoder from *Flashlight* :cite:`kahn2022flashlight`. .. devices:: CPU Note: To build the decoder, please use the factory function :func:`ctc_decoder`. c xXlX0lX@lURRU5UlURRU5n /n U(aB[ XCX%U 5n URU 5n Sn [ UU UU URU U U 5UlO[XeXRU 5UlXPl g)a Args: nbest (int): number of best decodings to return lexicon (Dict or None): lexicon mapping of words to spellings, or None for lexicon-free decoder word_dict (_Dictionary): dictionary of words tokens_dict (_Dictionary): dictionary of tokens lm (CTCDecoderLM): language model. If using a lexicon, only word level LMs are currently supported decoder_options (_LexiconDecoderOptions or _LexiconFreeDecoderOptions): parameters used for beam search decoding blank_token (str): token corresopnding to blank sil_token (str): token corresponding to silence unk_word (str): word corresponding to unknown FN) nbestr2r1r+blankr?_LexiconDecoderdecoder_LexiconFreeDecoderr%)rbrr#r2r1r%decoder_options blank_token sil_tokenrIr3 transitionsr5token_lms r>__init__CTCDecoder.__init__s4 "&%%// < "",,Y7 ";7PD **84HH*  DL/GZZYdeDL r\c^S[R"U55n[U4SjU5n[R"[ U55$)Nc3*# UH oSv M g7f)rNrT).0gs r> )CTCDecoder._get_tokens..s/.!.sc">UTR:g$rA)r)xrbs r>(CTCDecoder._get_tokens..s TZZr\)itgroupbyfiltertorch LongTensorlist)rbidxss` r> _get_tokensCTCDecoder._get_tokenss8/bjj.//6T ++r\c/n[U5H:up4X@R:XaMUS:Xd XAUS- :wdM)URU5 M< [R"U5$)z8Returns frame numbers corresponding to non-blank tokens.r) enumeraterappendr IntTensor)rbrrSrJidxs r>_get_timestepsCTCDecoder._get_timestepssY oFAjj AvQU +  # & y))r\c8URR5 g)zInitialize the internal state of the decoder. See :py:meth:`decode_step` for the usage. .. note:: This method is required only when performing online decoding. It is not necessary when performing batch decoding with :py:meth:`__call__`. N)r decode_beginrbs r>rCTCDecoder.decode_begins !!#r\c8URR5 g)zFinalize the internal state of the decoder. See :py:meth:`decode_step` for the usage. .. note:: This method is required only when performing online decoding. It is not necessary when performing batch decoding with :py:meth:`__call__`. N)r decode_endrs r>rCTCDecoder.decode_ends !r\cUR[R:wa [S5eUR(d [ S5eUR 5(d [ S5eURS:wa[ SUR35eUR5up#URRUR5X#5 g)aPerform incremental decoding on top of the curent internal state. .. note:: This method is required only when performing online decoding. It is not necessary when performing batch decoding with :py:meth:`__call__`. Args: emissions (torch.FloatTensor): CPU tensor of shape `(frame, num_tokens)` storing sequences of probability distribution over labels; output of acoustic model. Example: >>> decoder = torchaudio.models.decoder.ctc_decoder(...) >>> decoder.decode_begin() >>> decoder.decode_step(emission1) >>> decoder.decode_step(emission2) >>> decoder.decode_end() >>> result = decoder.get_final_hypothesis() emissions must be float32.emissions must be a CPU tensor.emissions must be contiguous.zemissions must be 2D. Found N) dtyperfloat32 ValueErroris_cpu RuntimeError is_contiguousndimshapesizer decode_stepdata_ptr)rb emissionsTNs r>rCTCDecoder.decode_step s( ??emm +9: :@A A&&((>? ? >>Q !=ioo=NOP P~~   !3!3!5q_to_hypoCTCDecoder._to_hypoCs" " '' 6get_final_hypothesisCTCDecoder.get_final_hypothesisNs0,,779}}W\tzz233r\NcUR[R:wa [S5eUR(d [ S5eUR 5(d [ S5eURS:wa[ SUR35eUbUR(d [ S5eUR5up4nUc[R"U4U5nSn/n[U5HvnUR5Xh-URS 5--n URRXUU5n UR!UR#U SUR$55 Mx U$) a{ Performs batched offline decoding. .. note:: This method performs offline decoding in one go. To perform incremental decoding, please refer to :py:meth:`decode_step`. Args: emissions (torch.FloatTensor): CPU tensor of shape `(batch, frame, num_tokens)` storing sequences of probability distribution over labels; output of acoustic model. lengths (Tensor or None, optional): CPU tensor of shape `(batch, )` storing the valid length of in time axis of the output Tensor in each batch. Returns: List[List[CTCHypothesis]]: List of sorted best hypotheses for each audio sequence in the batch. rrrzemissions must be 3D. Found Nzlengths must be a CPU tensor.r)rrrrrrrrrrfullrFrstriderdecoderrr) rbrlengthsBrr float_byteshyposb emissions_ptrrs r>__call__CTCDecoder.__call__]s2, ??emm +9: :@A A&&((>? ? >>Q !=ioo=NOP P  w~~>? ?.."a ?jj!q)G qA%..0;?YEUEUVWEX3XXMll))-QGG LLw|'<= > r\c~UVs/sH+o RRUR55PM- sn$s snf)z Map raw token IDs into corresponding tokens Args: idxs (LongTensor): raw token IDs generated from decoder Returns: List: tokens corresponding to the input IDs )r1rGitem)rbrrs r>idxs_to_tokensCTCDecoder.idxs_to_tokenss3CGG$3  **388:6$GGGs2:)rrr%rr1r2)rror#zOptional[Dict]r2rBr1rBr%rrz9Union[_LexiconDecoderOptions, _LexiconFreeDecoderOptions]rrErrErIrErnNone)rrRrnrO)rrRrnrR)rtorch.FloatTensor)rnzList[CTCHypothesis]rA)rrrzOptional[torch.Tensor]rnzList[List[CTCHypothesis]])rrOrnr)rUrVrWrXrYrrrrrrrrrrr[rTr\r>rrs77 7 7 ! 7  7S7777 7r, * $ "!=F   4 OS0*05K0 "0d Hr\rr2rz-infF-|zc  Ub[U5[La [S5e[U5nU(aB[ U5n[ UU=(d UR 5UUU U U U [RS9 nO4[UU=(d UR 5UUU U [RS9n[XUUU5n[U5[La[c [S5e[UU5nO Uc [5n[UUUUUUU UUS9 $)aBuilds an instance of :class:`CTCDecoder`. Args: lexicon (str or None): lexicon file containing the possible words and corresponding spellings. Each line consists of a word and its space separated spelling. If `None`, uses lexicon-free decoding. tokens (str or List[str]): file or list containing valid tokens. If using a file, the expected format is for tokens mapping to the same index to be on the same line lm (str, CTCDecoderLM, or None, optional): either a path containing KenLM language model, custom language model of type `CTCDecoderLM`, or `None` if not using a language model lm_dict (str or None, optional): file consisting of the dictionary used for the LM, with a word per line sorted by LM index. If decoding with a lexicon, entries in lm_dict must also occur in the lexicon file. If `None`, dictionary for LM is constructed using the lexicon file. (Default: None) nbest (int, optional): number of best decodings to return (Default: 1) beam_size (int, optional): max number of hypos to hold after each decode step (Default: 50) beam_size_token (int, optional): max number of tokens to consider at each decode step. If `None`, it is set to the total number of tokens (Default: None) beam_threshold (float, optional): threshold for pruning hypothesis (Default: 50) lm_weight (float, optional): weight of language model (Default: 2) word_score (float, optional): word insertion score (Default: 0) unk_score (float, optional): unknown word insertion score (Default: -inf) sil_score (float, optional): silence insertion score (Default: 0) log_add (bool, optional): whether or not to use logadd when merging hypotheses (Default: False) blank_token (str, optional): token corresponding to blank (Default: "-") sil_token (str, optional): token corresponding to silence (Default: "|") unk_word (str, optional): word corresponding to unknown (Default: "") Returns: CTCDecoder: decoder Example >>> decoder = ctc_decoder( >>> lexicon="lexicon.txt", >>> tokens="tokens.txt", >>> lm="kenlm.bin", >>> ) >>> results = decoder(emissions) # List of shape (B, nbest) of Hypotheses z!lm_dict must be None or str type.) beam_sizebeam_size_tokenbeam_threshold lm_weight word_score unk_score sil_scorelog_addcriterion_type)rrrrrrrzflashlight-text is installed, but KenLM is not installed. Please refer to https://github.com/kpu/kenlm#python-module for how to install it.) rr#r2r1r%rrrrI)rDrErrB _load_words_LexiconDecoderOptionsr'_CriterionTypeCTC_LexiconFreeDecoderOptionsrL_KenLMr_ZeroLMr)r#r$r%rHrrrrrrrrrrrrIr1rr2s r>rrs rtG}C7<==f%Kg&0+G{/E/E/G)!)--  5+G{/E/E/G))-- wG[(KI Bx3 >d B "  Y  '  r\cpUS;a[US35eSU3n[US3US3US:waUS3S9$SS9$) N) librispeechzlibrispeech-3-gramzlibrispeech-4-gramzZ not supported. Must be one of ['librispeech-3-gram', 'librispeech-4-gram', 'librispeech']zdecoder-assets/z /lexicon.txtz /tokens.txtrz/lm.binr")r_PretrainedFiles)modelprefixs r>_get_filenamesr ss OOgo p  ug &F (,'%!&-!7fXW  >B r\c[U5n[UR5n[UR5nURb[UR5nOSn[ UUUS9$)a! Retrieves pretrained data files used for :func:`ctc_decoder`. Args: model (str): pretrained language model to download. Valid values are: ``"librispeech-3-gram"``, ``"librispeech-4-gram"`` and ``"librispeech"``. Returns: Object with the following attributes * ``lm``: path corresponding to downloaded language model, or ``None`` if the model is not associated with an lm * ``lexicon``: path corresponding to downloaded lexicon file * ``tokens``: path corresponding to downloaded tokens file Nr")rrr#r$r%r)rfiles lexicon_file tokens_filelm_files r>r r s]" 5 !E"5==1L!%,,/K xx!%((+   r\)"r# Optional[str]r$zUnion[str, List[str]]r%zUnion[str, CTCDecoderLM]rHrrrorrorz Optional[int]rrQrrQrrQrrQrrQrrrrErrErIrErnr)rrErnr)> __future__r itertoolsrabcr collectionsrtypingrrrr r r rflashlight.lib.text.decoderr rr rrrrrrrr_LMr_LMStaterr/rr(rrflashlight.lib.text.dictionaryrrCrrBrrtorchaudio.utilsr!flashlight.lib.text.decoder.kenlmrr Exception__all__rr?rLrrrrrQrrr rTr\r>rs""AA     -A /1LM  oJo*  @."3."bcHcHR$(!%)V}!n n !n !n n  n  n#nnnnnnnnn !n"#nb w? s*C!!D(C00C<8D;C<<D