fix u2 bins (#2643)

speechx/examples/u2pp_ol/wenetspeech/README.md

@@ -2,10 +2,10 @@
 
 ## Testing with Aishell Test Data
 
-## Download wav and model
+### Download wav and model
 
 ```
-run.sh --stop_stage 0
+./run.sh --stop_stage 0
 ```
 
 ### compute feature
@@ -22,7 +22,6 @@ run.sh --stop_stage 0
 
 ### decoding using wav
 
-
 ```
 ./run.sh --stage 3 --stop_stage 3
 ```

speechx/examples/u2pp_ol/wenetspeech/local/decode.sh

@@ -10,7 +10,7 @@ mkdir -p $exp
 ckpt_dir=./data/model
 model_dir=$ckpt_dir/asr1_chunk_conformer_u2pp_wenetspeech_static_1.3.0.model/
 
-utils/run.pl JOB=1:$nj $data/split${nj}/JOB/decoder.fbank.wolm.log \
+utils/run.pl JOB=1:$nj $data/split${nj}/JOB/decoder.log \
 ctc_prefix_beam_search_decoder_main \
     --model_path=$model_dir/export.jit \
     --vocab_path=$model_dir/unit.txt \

speechx/examples/u2pp_ol/wenetspeech/local/nnet.sh

@@ -1,18 +1,21 @@
 #!/bin/bash
-set -x
 set -e
 
 . path.sh
 
+nj=20
 data=data
 exp=exp
+
 mkdir -p $exp
 ckpt_dir=./data/model
 model_dir=$ckpt_dir/asr1_chunk_conformer_u2pp_wenetspeech_static_1.3.0.model/
 
+utils/run.pl JOB=1:$nj $data/split${nj}/JOB/nnet.log \
 u2_nnet_main \
     --model_path=$model_dir/export.jit \
-    --feature_rspecifier=ark,t:$exp/fbank.ark \
+    --vocab_path=$model_dir/unit.txt \
+    --feature_rspecifier=ark,t:${data}/split${nj}/JOB/fbank.ark \
     --nnet_decoder_chunk=16 \
     --receptive_field_length=7 \
     --subsampling_rate=4 \
@@ -20,4 +23,3 @@ u2_nnet_main \
     --nnet_encoder_outs_wspecifier=ark,t:$exp/encoder_outs.ark \
     --nnet_prob_wspecifier=ark,t:$exp/logprobs.ark
 echo "u2 nnet decode."
-

speechx/examples/u2pp_ol/wenetspeech/run.sh

@@ -24,8 +24,6 @@ fi
 
 
 ckpt_dir=$data/model
-model_dir=$ckpt_dir/asr1_chunk_conformer_u2pp_wenetspeech_static_1.3.0.model/
-
 
 if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ];then
     #  download u2pp model

speechx/speechx/frontend/audio/data_cache.h

@@ -32,7 +32,6 @@ class DataCache : public FrontendInterface {
     // accept waves/feats
     void Accept(const kaldi::VectorBase<kaldi::BaseFloat>& inputs) override {
         data_ = inputs;
-        SetDim(data_.Dim());
     }
 
     bool Read(kaldi::Vector<kaldi::BaseFloat>* feats) override {
@@ -41,7 +40,6 @@ class DataCache : public FrontendInterface {
         }
         (*feats) = data_;
         data_.Resize(0);
-        SetDim(data_.Dim());
         return true;
     }
 

speechx/speechx/nnet/decodable.cc

@@ -71,6 +71,7 @@ bool Decodable::AdvanceChunk() {
         VLOG(3) << "decodable exit;";
         return false;
     }
+    CHECK_GE(frontend_->Dim(), 0);
     VLOG(1) << "AdvanceChunk feat cost: " << timer.Elapsed() << " sec.";
     VLOG(2) << "Forward in " << features.Dim() / frontend_->Dim() << " feats.";