fix

examples/csmsc/voc1/README.md

@@ -17,6 +17,7 @@ Run the command below to
 3. train the model.
 4. synthesize wavs.
     - synthesize waveform from `metadata.jsonl`.
+    - synthesize waveform from text file.
 ```bash
 ./run.sh
 ```
@@ -126,6 +127,67 @@ optional arguments:
 4. `--output-dir` is the directory to save the synthesized audio files.
 5. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.
 
+`./local/synthesize_e2e.sh` calls `${BIN_DIR}/../synthesize_e2e.py`, which can synthesize waveform from text file.
+```bash
+CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name}
+```
+```text
+usage: synthesize_e2e.py [-h]
+                         [--am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech}]
+                         [--am_config AM_CONFIG] [--am_ckpt AM_CKPT]
+                         [--am_stat AM_STAT] [--phones_dict PHONES_DICT]
+                         [--tones_dict TONES_DICT]
+                         [--speaker_dict SPEAKER_DICT] [--spk_id SPK_ID]
+                         [--voc {pwgan_csmsc,pwgan_ljspeech,pwgan_aishell3,pwgan_vctk,mb_melgan_csmsc,style_melgan_csmsc,hifigan_csmsc,hifigan_ljspeech,hifigan_aishell3,hifigan_vctk,wavernn_csmsc}]
+                         [--voc_config VOC_CONFIG] [--voc_ckpt VOC_CKPT]
+                         [--voc_stat VOC_STAT] [--lang LANG]
+                         [--inference_dir INFERENCE_DIR] [--ngpu NGPU]
+                         [--text TEXT] [--output_dir OUTPUT_DIR]
+
+Synthesize with acoustic model & vocoder
+
+optional arguments:
+  -h, --help            show this help message and exit
+  --am {speedyspeech_csmsc,speedyspeech_aishell3,fastspeech2_csmsc,fastspeech2_ljspeech,fastspeech2_aishell3,fastspeech2_vctk,tacotron2_csmsc,tacotron2_ljspeech}
+                        Choose acoustic model type of tts task.
+  --am_config AM_CONFIG
+                        Config of acoustic model.
+  --am_ckpt AM_CKPT     Checkpoint file of acoustic model.
+  --am_stat AM_STAT     mean and standard deviation used to normalize
+                        spectrogram when training acoustic model.
+  --phones_dict PHONES_DICT
+                        phone vocabulary file.
+  --tones_dict TONES_DICT
+                        tone vocabulary file.
+  --speaker_dict SPEAKER_DICT
+                        speaker id map file.
+  --spk_id SPK_ID       spk id for multi speaker acoustic model
+  --voc {pwgan_csmsc,pwgan_ljspeech,pwgan_aishell3,pwgan_vctk,mb_melgan_csmsc,style_melgan_csmsc,hifigan_csmsc,hifigan_ljspeech,hifigan_aishell3,hifigan_vctk,wavernn_csmsc}
+                        Choose vocoder type of tts task.
+  --voc_config VOC_CONFIG
+                        Config of voc.
+  --voc_ckpt VOC_CKPT   Checkpoint file of voc.
+  --voc_stat VOC_STAT   mean and standard deviation used to normalize
+                        spectrogram when training voc.
+  --lang LANG           Choose model language. zh or en
+  --inference_dir INFERENCE_DIR
+                        dir to save inference models
+  --ngpu NGPU           if ngpu == 0, use cpu.
+  --text TEXT           text to synthesize, a 'utt_id sentence' pair per line.
+  --output_dir OUTPUT_DIR
+                        output dir.
+
+```
+1. `--am` is acoustic model type with the format {model_name}_{dataset}
+2. `--am_config`, `--am_ckpt`, `--am_stat` and `--phones_dict` are arguments for acoustic model, which correspond to the 4 files in the fastspeech2 pretrained model.
+3. `--voc` is vocoder type with the format {model_name}_{dataset}
+4. `--voc_config`, `--voc_ckpt`, `--voc_stat` are arguments for vocoder, which correspond to the 3 files in the parallel wavegan pretrained model.
+5. `--lang` is the model language, which can be `zh` or `en`.
+6. `--test_metadata` should be the metadata file in the normalized subfolder of `test`  in the `dump` folder.
+7. `--text` is the text file, which contains sentences to synthesize.
+8. `--output_dir` is the directory to save synthesized audio files.
+9. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.
+
 ## Pretrained Models
 The pretrained model can be downloaded here:
 - [pwg_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_ckpt_0.4.zip)

examples/csmsc/voc1/local/synthesize_e2e.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+config_path=$1
+train_output_path=$2
+ckpt_name=$3
+
+
+FLAGS_allocator_strategy=naive_best_fit \
+FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+python3 ${BIN_DIR}/../../synthesize_e2e.py \
+    --am=fastspeech2_csmsc \
+    --am_config=${config_path} \
+    --am_ckpt=fastspeech2_nosil_baker_ckpt_0.4/snapshot_iter_76000.pdz \
+    --am_stat=dump/train/speech_stats.npy \
+    --voc=pwgan_csmsc \
+    --voc_config=pwg_baker_ckpt_0.4/pwg_default.yaml \
+    --voc_ckpt=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz \
+    --voc_stat=pwg_baker_ckpt_0.4/pwg_stats.npy \
+    --lang=zh \
+    --text=${BIN_DIR}/../../assets/sentences.txt \
+    --output_dir=${train_output_path}/test_e2e \
+    --phones_dict=fastspeech2_nosil_baker_ckpt_0.4//phone_id_map.txt \
+    --inference_dir=${train_output_path}/inference

examples/csmsc/voc1/run.sh

@@ -31,7 +31,12 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
     CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
 fi
 
-# PTQ_static
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    # synthesize_e2e, vocoder is pwgan by default
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/synthesize_e2e.sh ${conf_path} ${train_output_path} ${ckpt_name} || exit -1
+fi
+
+# PTQ_static
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
     CUDA_VISIBLE_DEVICES=${gpus} ./local/PTQ_static.sh  ${train_output_path} pwgan_csmsc || exit -1
 fi