kaldi 源码分析(九) - topo 文件分析-白红宇

在 egs/wsj/s5/steps/nnet3/chain/gen_topo*.py 与 src/hmm/hmm-topology.cc 文件进行对应

在 gen_topo*.p{l, y} 文件中进行自动创建 topo 文件，然后在 hmm-topology.cc 文件中的 HmmTopology::Read() 函数中解析 topo 文件生成 HmmTopology 对象。

在 steps/nnet3/chain/gen_topo*.p{l, y} 文件中可以看到 topo 文件大致结构：

args = parser.parse_args()silence_phones = [ int(x) for x in args.silence_phones.split(":") ]nonsilence_phones = [ int(x) for x in args.nonsilence_phones.split(":") ]all_phones = silence_phones +  nonsilence_phonesprint("
     
      ")print("
      
       ")# 当前 TopologyEntry 配置相关的所有 Phone 元素print("
       
        ")print(" ".join([str(x) for x in all_phones]))print("
       ")# 当前 State 配置相关# state 0 is nonemittingprint("
       
         0 
        
          1 0.5 
         
           2 0.5 
         
        
       ")# state 1 is for when we traverse it in 1 stateprint("
       
         1 
        
          0 
         
           4 1.0 
         
        
       ")# state 2 is for when we traverse it in >1 state, for the first state.print("
       
         2 
        
          2 
         
           3 1.0 
         
        
       ")# state 3 is for the self-loop.  Use pdf-class 1 here so that the default# phone-class clustering (which uses only pdf-class 1 by default) gets only# stats from longer phones.print("
       
         3 
        
          1 
         
           3 0.5 
          
            4 0.5 
          
         
        
       ")print("
       
         4 
       ")print("
      ")print("
     ")

在 hmm-topology.h 文件中

/// TopologyEntry is a typedef that represents the topology of  /// a single (prototype) state.  typedef std::vector
     
       TopologyEntry;

对于 HmmTopology::Read() 函数中可以了解 topo 文件解析的过程

ExpectToken(is, binary, "
     
      ");        std::vector
      
        phones;        std::string s;        // 获取所有 phones 列表        while (1) {          is >> s;          if (is.fail()) KALDI_ERR << "Reading HmmTopology object, unexpected end of file while expecting phones.";          if (s == "
      
     ") break;          else {            int32 phone;            if (!ConvertStringToInteger(s, &phone))              KALDI_ERR << "Reading HmmTopology object, expected "                        << "integer, got instead " << s;            phones.push_back(phone);          }        }        // 构建状态转换概率        std::vector
     
       this_entry;        std::string token;        ReadToken(is, binary, &token);        while (token != "") {          if (token != "
      
       ")            KALDI_ERR << "Expected  or 
       
        , got instead "<
        
         (this_entry.size()))            KALDI_ERR << "States are expected to be in order from zero, expected "                      << this_entry.size() <<  ", got " << state;          ReadToken(is, binary, &token);          int32 forward_pdf_class = kNoPdf;  // -1 by default, means no pdf.          if (token == "
         
          ") {            // 根据 pdfClass 来创建一个 HmmState            ReadBasicType(is, binary, &forward_pdf_class);            this_entry.push_back(HmmState(forward_pdf_class));            ReadToken(is, binary, &token);            if (token == "
          
           ") KALDI_ERR << "pdf classes should be defined using 
           
             " << "or 
            
             /
             
               pair"; } else if (token == "
              
               ") { // 根据 
                
                
                  组合, 来创建一个 HmmState int32 self_loop_pdf_class = kNoPdf; ReadBasicType(is, binary, &forward_pdf_class); ReadToken(is, binary, &token); KALDI_ASSERT(token == "
                 
                  "); ReadBasicType(is, binary, &self_loop_pdf_class); this_entry.push_back(HmmState(forward_pdf_class, self_loop_pdf_class)); ReadToken(is, binary, &token); } else { // 若 
                  
                    后没有 
                   
                    , 
                    
                      , 则添加 kNoPdf 的 HmmState this_entry.push_back(HmmState(forward_pdf_class)); } while (token == "
                     
                      ") { int32 dst_state; BaseFloat trans_prob; ReadBasicType(is, binary, &dst_state); ReadBasicType(is, binary, &trans_prob); // 获取最后一个 HmmState 状态 并将 transitions 中配置 状态切换的概率 this_entry.back().transitions.push_back(std::make_pair(dst_state, trans_prob)); ReadToken(is, binary, &token); } if(token == "
                      
                       ") // TODO: remove this clause after a while. KALDI_ERR << "You are trying to read old-format topology with new Kaldi."; if (token != "
                      
                     
                    
                   
                  ") KALDI_ERR << "Reading HmmTopology, unexpected token "<
                  
                   (phone2idx_.size()) <= phone) phone2idx_.resize(phone+1, -1); // -1 is invalid index. KALDI_ASSERT(phone > 0); if (phone2idx_[phone] != -1) KALDI_ERR << "Phone with index "<<(i)<<" appears in multiple topology entries."; // 这里将每个 phone 相关的 HmmState 切换过程TopologyEntry的 index 设置到 phone2idx 中 phone2idx_[phone] = my_index; phones_.push_back(phone); }