[speechx]add wfst decoder #2886
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
zh794390558
reviewed
Feb 7, 2023
| @@ -45,7 +45,7 @@ class CTCPrefixBeamSearch : public DecoderBase { | |||
|
|
|||
| void FinalizeSearch(); | |||
|
|
|||
| const std::shared_ptr<fst::SymbolTable> VocabTable() const { | |||
| const std::shared_ptr<fst::SymbolTable> WordSymbolTable() const override { | |||
There was a problem hiding this comment.
unit table 应该是模型的输出，不一定是 word
| @@ -15,7 +15,7 @@ | |||
| #include "decoder/ctc_tlg_decoder.h" | |||
| namespace ppspeech { | |||
|
|
|||
| TLGDecoder::TLGDecoder(TLGDecoderOptions opts) { | |||
| TLGDecoder::TLGDecoder(TLGDecoderOptions opts) : opts_(opts) { | |||
| fst_.reset(fst::Fst<fst::StdArc>::Read(opts.fst_path)); | |||
| LOG(INFO) << "chunk size (frame): " << chunk_size; | ||
| LOG(INFO) << "chunk stride (frame): " << chunk_stride; | ||
| LOG(INFO) << "receptive field (frame): " << receptive_field_length; | ||
| new ppspeech::Decodable(nnet_producer, FLAGS_acoustic_scale)); |
| decoder_.reset(new CTCPrefixBeamSearch( | ||
| resource.vocab_path, resource.decoder_opts.ctc_prefix_search_opts)); | ||
| if (resource.decoder_opts.tlg_decoder_opts.fst_path == "") { | ||
| decoder_.reset(new CTCPrefixBeamSearch( |
|
|
||
| unit_table_ = decoder_->VocabTable(); |
There was a problem hiding this comment.
unit_table 指的 model 的vocab，
symbol_table 应该指的是 fst 的 olabel 对应的table吧？
英文的时候这个不能混。
There was a problem hiding this comment.
这个不是额，fst 的 input or output lable 都可以对应symbol table； 主要是vocab不是很合适；unit_table 建模单元可以看做事symbol table的一部分；中文的字 与 词 有点混淆，但是这不是问题。
| @@ -214,7 +218,7 @@ void U2Recognizer::UpdateResult(bool finish) { | |||
|
|
|||
| void U2Recognizer::AttentionRescoring() { | |||
| decoder_->FinalizeSearch(); | |||
| UpdateResult(true); | |||
| UpdateResult(false); | |||
There was a problem hiding this comment.
不更新time line而已；后续整理上去，timeline 还没有矫正；
| @@ -154,10 +165,9 @@ class U2Recognizer { | |||
|
|
|||
| std::shared_ptr<NnetProducer> nnet_producer_; | |||
| std::shared_ptr<Decodable> decodable_; | |||
| std::unique_ptr<CTCPrefixBeamSearch> decoder_; | |||
| std::unique_ptr<DecoderBase> decoder_; | |||
There was a problem hiding this comment.
这个非共享指针，会在refactor时都变成 unique_ptr；
|
|
||
| // e2e unit symbol table | ||
| std::shared_ptr<fst::SymbolTable> unit_table_ = nullptr; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR types
New features
PR changes
Others
Describe
add wfst decoder