more doc for speechx

speechx/examples/custom_asr/README.md

@@ -1,4 +1,4 @@
-# customized Auto Speech Recognition
+# Customized ASR
 
 ## introduction
 These scripts are tutorials to show you how build your own decoding graph.

speechx/examples/ds2_ol/README.md

@@ -4,3 +4,4 @@
 
 * `websocket` - Streaming ASR with websocket for deepspeech2_aishell.    
 * `aishell` - Streaming Decoding under aishell dataset, for local WER test.    
+* `onnx` - Example to convert deepspeech2 to onnx format.

speechx/examples/ds2_ol/aishell/README.md

@@ -1,12 +1,57 @@
 # Aishell - Deepspeech2 Streaming
 
-## How to run
+> We recommend using U2/U2++ model instead of DS2, please see [here](../../u2pp_ol/wenetspeech/).
 
+A C++ deployment example for using the deepspeech2 model to recognize `wav` and compute `CER`. We using AISHELL-1 as test data.
+
+## Source path.sh
+
+```bash
+. path.sh
 ```
+
+SpeechX bins is under `echo $SPEECHX_BUILD`, more info please see `path.sh`.
+
+## Recognize with linear feature
+
+```bash
 bash run.sh
 ```
 
-## Results
+`run.sh` has multi stage, for details please see `run.sh`: 
+
+1. donwload dataset, model and lm
+2. convert cmvn format and compute feature
+3. decode w/o lm by feature
+4. decode w/ ngram lm by feature
+5. decode w/ TLG graph by feature
+6. recognize w/ TLG graph by wav input
+
+### Recognize with `.scp` file for wav
+
+This sciprt using `recognizer_main` to recognize wav file.
+
+The input is `scp` file which look like this:
+```text
+# head data/split1/1/aishell_test.scp 
+BAC009S0764W0121        /workspace/PaddleSpeech/speechx/examples/u2pp_ol/wenetspeech/data/test/S0764/BAC009S0764W0121.wav
+BAC009S0764W0122        /workspace/PaddleSpeech/speechx/examples/u2pp_ol/wenetspeech/data/test/S0764/BAC009S0764W0122.wav
+...
+BAC009S0764W0125        /workspace/PaddleSpeech/speechx/examples/u2pp_ol/wenetspeech/data/test/S0764/BAC009S0764W0125.wav
+```
+
+If you want to recognize one wav, you can make `scp` file like this:
+```text
+key  path/to/wav/file
+```
+
+Then specify `--wav_rspecifier=` param for `recognizer_main` bin. For other flags meaning, please see `help`:
+```bash
+recognizer_main --help
+```
+
+For the exmaple to using `recognizer_main` please see `run.sh`.
+
 
 ### CTC Prefix Beam Search w/o LM
 
@@ -25,7 +70,7 @@ Mandarin -> 7.86 % N=104768 C=96865 S=7573 D=330 I=327
 Other -> 0.00 % N=0 C=0 S=0 D=0 I=0
 ```
 
-### CTC WFST
+### CTC TLG WFST
 
 LM: [aishell train](http://paddlespeech.bj.bcebos.com/speechx/examples/ds2_ol/aishell/aishell_graph.zip)
 --acoustic_scale=1.2
@@ -43,8 +88,11 @@ Mandarin -> 10.93 % N=104762 C=93410 S=9779 D=1573 I=95
 Other -> 100.00 % N=3 C=0 S=1 D=2 I=0
 ```
 
-## fbank
-```
+## Recognize with fbank feature
+
+This script is same to `run.sh`, but using fbank feature.
+
+```bash
 bash run_fbank.sh
 ```
 
@@ -66,7 +114,7 @@ Mandarin -> 5.82 % N=104762 C=99386 S=4941 D=435 I=720
 English -> 0.00 % N=0 C=0 S=0 D=0 I=0
 ```
 
-### CTC WFST
+### CTC TLG WFST
 
 LM: [aishell train](https://paddlespeech.bj.bcebos.com/s2t/paddle_asr_online/aishell_graph2.zip)
 ```
@@ -75,7 +123,11 @@ Mandarin -> 9.57 % N=104762 C=94817 S=4325 D=5620 I=84
 Other -> 100.00 % N=3 C=0 S=1 D=2 I=0
 ```
 
-## build TLG graph 
-```
- bash run_build_tlg.sh
+## Build TLG WFST graph 
+
+The script is for building TLG wfst graph, depending on `srilm`, please make sure it is installed.
+For more information please see the script below.
+
+```bash
+ bash ./local/run_build_tlg.sh
 ```

speechx/examples/ds2_ol/aishell/local/run_build_tlg.sh

@@ -22,6 +22,7 @@ mkdir -p $data
 
 if [ $stage -le -1 ] && [ $stop_stage -ge -1 ]; then
     if [ ! -f $data/speech.ngram.zh.tar.gz ];then
+        # download ngram
         pushd $data
         wget -c http://paddlespeech.bj.bcebos.com/speechx/examples/ngram/zh/speech.ngram.zh.tar.gz
         tar xvzf speech.ngram.zh.tar.gz
@@ -29,6 +30,7 @@ if [ $stage -le -1 ] && [ $stop_stage -ge -1 ]; then
     fi
 
     if [ ! -f $ckpt_dir/data/mean_std.json ]; then
+        # download model
         mkdir -p $ckpt_dir
         pushd $ckpt_dir
         wget -c https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr0/WIP1_asr0_deepspeech2_online_wenetspeech_ckpt_1.0.0a.model.tar.gz
@@ -43,6 +45,7 @@ if [ ! -f $unit ]; then
 fi
 
 if ! which ngram-count; then
+    # need srilm install
     pushd $MAIN_ROOT/tools
     make srilm.done
     popd
@@ -71,7 +74,7 @@ lm=data/local/lm
 mkdir -p $lm
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
-    # Train lm
+    # Train ngram lm
     cp $text $lm/text
     local/aishell_train_lms.sh
     echo "build LM done."
@@ -94,8 +97,8 @@ cmvn=$data/cmvn_fbank.ark
 wfst=$data/lang_test
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
-
     if [ ! -d $data/test ]; then
+        # download test dataset
         pushd $data
         wget -c https://paddlespeech.bj.bcebos.com/s2t/paddle_asr_online/aishell_test.zip
         unzip  aishell_test.zip
@@ -108,6 +111,7 @@ if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
 
     ./local/split_data.sh $data $data/$aishell_wav_scp $aishell_wav_scp $nj
     
+    # convert cmvn format
     cmvn-json2kaldi --json_file=$ckpt_dir/data/mean_std.json --cmvn_write_path=$cmvn
 fi
 
@@ -116,7 +120,7 @@ label_file=aishell_result
 export GLOG_logtostderr=1
 
 if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
-    #  TLG decoder
+    #  recognize w/ TLG graph
     utils/run.pl JOB=1:$nj $data/split${nj}/JOB/check_tlg.log \
     recognizer_main \
         --wav_rspecifier=scp:$data/split${nj}/JOB/${aishell_wav_scp} \

speechx/examples/ds2_ol/aishell/run.sh

@@ -32,6 +32,7 @@ exp=$PWD/exp
 aishell_wav_scp=aishell_test.scp
 if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ];then
     if [ ! -d $data/test ]; then
+        # donwload dataset
         pushd $data
         wget -c https://paddlespeech.bj.bcebos.com/s2t/paddle_asr_online/aishell_test.zip
         unzip  aishell_test.zip
@@ -43,6 +44,7 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ];then
     fi
 
     if [ ! -f $ckpt_dir/data/mean_std.json ]; then
+        # download model
         mkdir -p $ckpt_dir
         pushd $ckpt_dir
         wget -c https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_online_aishell_ckpt_0.2.0.model.tar.gz
@@ -52,6 +54,7 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ];then
 
     lm=$data/zh_giga.no_cna_cmn.prune01244.klm
     if [ ! -f $lm ]; then
+        # download kenlm bin
         pushd $data
         wget -c https://deepspeech.bj.bcebos.com/zh_lm/zh_giga.no_cna_cmn.prune01244.klm
         popd
@@ -68,7 +71,7 @@ export GLOG_logtostderr=1
 
 cmvn=$data/cmvn.ark
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
-    # 3. gen linear feat
+    # 3. convert cmvn format and compute linear feat
     cmvn_json2kaldi_main --json_file=$ckpt_dir/data/mean_std.json --cmvn_write_path=$cmvn
 
     ./local/split_data.sh $data $data/$aishell_wav_scp $aishell_wav_scp $nj
@@ -82,14 +85,14 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
-    #  recognizer
+    #  decode w/o lm
     utils/run.pl JOB=1:$nj $data/split${nj}/JOB/recog.wolm.log \
     ctc_beam_search_decoder_main \
         --feature_rspecifier=scp:$data/split${nj}/JOB/feat.scp \
         --model_path=$model_dir/avg_1.jit.pdmodel \
         --param_path=$model_dir/avg_1.jit.pdiparams \
         --model_output_names=softmax_0.tmp_0,tmp_5,concat_0.tmp_0,concat_1.tmp_0 \
-	--nnet_decoder_chunk=8 \
+	    --nnet_decoder_chunk=8 \
         --dict_file=$vocb_dir/vocab.txt \
         --result_wspecifier=ark,t:$data/split${nj}/JOB/result
 
@@ -101,14 +104,14 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
 fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
-    #  decode with lm
+    # decode w/ ngram lm with feature input
     utils/run.pl JOB=1:$nj $data/split${nj}/JOB/recog.lm.log \
     ctc_beam_search_decoder_main \
         --feature_rspecifier=scp:$data/split${nj}/JOB/feat.scp \
         --model_path=$model_dir/avg_1.jit.pdmodel \
         --param_path=$model_dir/avg_1.jit.pdiparams \
         --model_output_names=softmax_0.tmp_0,tmp_5,concat_0.tmp_0,concat_1.tmp_0 \
-	--nnet_decoder_chunk=8 \
+	    --nnet_decoder_chunk=8 \
         --dict_file=$vocb_dir/vocab.txt \
         --lm_path=$lm \
         --result_wspecifier=ark,t:$data/split${nj}/JOB/result_lm
@@ -124,6 +127,7 @@ wfst=$data/wfst/
 if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
     mkdir -p $wfst
     if [ ! -f $wfst/aishell_graph.zip ]; then
+        # download TLG graph
         pushd $wfst
         wget -c https://paddlespeech.bj.bcebos.com/s2t/paddle_asr_online/aishell_graph.zip
         unzip aishell_graph.zip
@@ -133,7 +137,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
 fi
 
 if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
-    #  TLG decoder
+    #  decoder w/ TLG graph with feature input
     utils/run.pl JOB=1:$nj $data/split${nj}/JOB/recog.wfst.log \
     ctc_tlg_decoder_main \
         --feature_rspecifier=scp:$data/split${nj}/JOB/feat.scp \
@@ -142,7 +146,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
         --word_symbol_table=$wfst/words.txt \
         --model_output_names=softmax_0.tmp_0,tmp_5,concat_0.tmp_0,concat_1.tmp_0 \
         --graph_path=$wfst/TLG.fst --max_active=7500 \
-	--nnet_decoder_chunk=8 \
+	    --nnet_decoder_chunk=8 \
         --acoustic_scale=1.2 \
         --result_wspecifier=ark,t:$data/split${nj}/JOB/result_tlg
 
@@ -154,7 +158,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
 fi
 
 if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
-    #  TLG decoder
+    #  recognize from wav file w/ TLG graph
     utils/run.pl JOB=1:$nj $data/split${nj}/JOB/recognizer.log \
     recognizer_main \
         --wav_rspecifier=scp:$data/split${nj}/JOB/${aishell_wav_scp} \
@@ -162,7 +166,7 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
         --model_path=$model_dir/avg_1.jit.pdmodel \
         --param_path=$model_dir/avg_1.jit.pdiparams \
         --word_symbol_table=$wfst/words.txt \
-	--nnet_decoder_chunk=8 \
+	    --nnet_decoder_chunk=8 \
         --model_output_names=softmax_0.tmp_0,tmp_5,concat_0.tmp_0,concat_1.tmp_0 \
         --graph_path=$wfst/TLG.fst --max_active=7500 \
         --acoustic_scale=1.2 \

speechx/examples/ds2_ol/aishell/run_fbank.sh

@@ -68,7 +68,7 @@ export GLOG_logtostderr=1
 
 cmvn=$data/cmvn_fbank.ark
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
-    # 3. gen linear feat
+    # 3. convert cmvn format and compute fbank feat
     cmvn_json2kaldi_main --json_file=$ckpt_dir/data/mean_std.json --cmvn_write_path=$cmvn --binary=false
 
     ./local/split_data.sh $data $data/$aishell_wav_scp $aishell_wav_scp $nj
@@ -82,7 +82,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
-    #  recognizer
+    #  decode w/ lm by feature
     utils/run.pl JOB=1:$nj $data/split${nj}/JOB/recog.fbank.wolm.log \
     ctc_beam_search_decoder_main \
         --feature_rspecifier=scp:$data/split${nj}/JOB/fbank_feat.scp \
@@ -90,7 +90,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
         --param_path=$model_dir/avg_5.jit.pdiparams \
         --model_output_names=softmax_0.tmp_0,tmp_5,concat_0.tmp_0,concat_1.tmp_0 \
     	--model_cache_shapes="5-1-2048,5-1-2048" \
-	--nnet_decoder_chunk=8 \
+	    --nnet_decoder_chunk=8 \
         --dict_file=$vocb_dir/vocab.txt \
         --result_wspecifier=ark,t:$data/split${nj}/JOB/result_fbank
 
@@ -100,15 +100,15 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
 fi
 
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
-    #  decode with lm
+    #  decode with ngram lm by feature
     utils/run.pl JOB=1:$nj $data/split${nj}/JOB/recog.fbank.lm.log \
     ctc_beam_search_decoder_main \
         --feature_rspecifier=scp:$data/split${nj}/JOB/fbank_feat.scp \
         --model_path=$model_dir/avg_5.jit.pdmodel \
         --param_path=$model_dir/avg_5.jit.pdiparams \
         --model_output_names=softmax_0.tmp_0,tmp_5,concat_0.tmp_0,concat_1.tmp_0 \
-	--model_cache_shapes="5-1-2048,5-1-2048" \
-	--nnet_decoder_chunk=8 \
+	    --model_cache_shapes="5-1-2048,5-1-2048" \
+	    --nnet_decoder_chunk=8 \
         --dict_file=$vocb_dir/vocab.txt \
         --lm_path=$lm \
         --result_wspecifier=ark,t:$data/split${nj}/JOB/fbank_result_lm
@@ -131,7 +131,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
 fi
 
 if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
-    #  TLG decoder
+    #  decode w/ TLG graph by feature
     utils/run.pl JOB=1:$nj $data/split${nj}/JOB/recog.fbank.wfst.log \
     ctc_tlg_decoder_main \
         --feature_rspecifier=scp:$data/split${nj}/JOB/fbank_feat.scp \
@@ -139,8 +139,8 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
         --param_path=$model_dir/avg_5.jit.pdiparams \
         --word_symbol_table=$wfst/words.txt \
         --model_output_names=softmax_0.tmp_0,tmp_5,concat_0.tmp_0,concat_1.tmp_0 \
-	--model_cache_shapes="5-1-2048,5-1-2048" \
-	--nnet_decoder_chunk=8 \
+	    --model_cache_shapes="5-1-2048,5-1-2048" \
+	    --nnet_decoder_chunk=8 \
         --graph_path=$wfst/TLG.fst --max_active=7500 \
         --acoustic_scale=1.2 \
         --result_wspecifier=ark,t:$data/split${nj}/JOB/result_tlg
@@ -153,6 +153,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
 fi
 
 if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
+    # recgonize w/ TLG graph by wav
     utils/run.pl JOB=1:$nj $data/split${nj}/JOB/fbank_recognizer.log \
     recognizer_main \
         --wav_rspecifier=scp:$data/split${nj}/JOB/${aishell_wav_scp} \
@@ -163,7 +164,7 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
         --word_symbol_table=$wfst/words.txt \
         --model_output_names=softmax_0.tmp_0,tmp_5,concat_0.tmp_0,concat_1.tmp_0 \
         --model_cache_shapes="5-1-2048,5-1-2048" \
-	--nnet_decoder_chunk=8 \
+	    --nnet_decoder_chunk=8 \
         --graph_path=$wfst/TLG.fst --max_active=7500 \
         --acoustic_scale=1.2 \
         --result_wspecifier=ark,t:$data/split${nj}/JOB/result_fbank_recognizer

speechx/examples/u2pp_ol/wenetspeech/README.md

@@ -6,13 +6,14 @@ This example will demonstrate how to using the u2/u2++ model to recognize `wav`
 
 ## Testing with Aishell Test Data
 
-### Source `path.sh` first 
+## Source path.sh
 
 ```bash
-source path.sh
+. path.sh
 ```
 
-All bins are under `echo $SPEECHX_BUILD` dir.
+SpeechX bins is under `echo $SPEECHX_BUILD`, more info please see `path.sh`.
+
 
 ### Download dataset and model
 

speechx/examples/u2pp_ol/wenetspeech/run.sh

@@ -85,3 +85,8 @@ if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
     # decode with wav input
     ./loca/recognizer.sh
 fi
+
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+    # decode with wav input with quanted model
+    ./loca/recognizer_quant.sh
+fi