Merge pull request #1581 from yt605155624/add_aishell3_hifigan

[TTS]Add aishell3 hifigan
2 years ago · 0b4270575f
parent 62cee69c88 5ab2601759
commit 0b4270575f
6 changed files with 117 additions and 38 deletions
--- a/docs/source/released_model.md
+++ b/docs/source/released_model.md
@ -49,11 +49,12 @@ Model Type | Dataset| Example Link | Pretrained Models| Static Models|Size (stat
 WaveFlow| LJSpeech |[waveflow-ljspeech](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/voc0)|[waveflow_ljspeech_ckpt_0.3.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/waveflow/waveflow_ljspeech_ckpt_0.3.zip)|||
 Parallel WaveGAN| CSMSC |[PWGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc1)|[pwg_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_ckpt_0.4.zip)|[pwg_baker_static_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_static_0.4.zip)|5.1MB|
 Parallel WaveGAN| LJSpeech |[PWGAN-ljspeech](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/voc1)|[pwg_ljspeech_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_ljspeech_ckpt_0.5.zip)|||
-Parallel WaveGAN|AISHELL-3 |[PWGAN-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc1)|[pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip)|||
+Parallel WaveGAN| AISHELL-3 |[PWGAN-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc1)|[pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip)|||
 Parallel WaveGAN| VCTK |[PWGAN-vctk](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/vctk/voc1)|[pwg_vctk_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_vctk_ckpt_0.5.zip)|||
 |Multi Band MelGAN | CSMSC |[MB MelGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc3) | [mb_melgan_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/mb_melgan/mb_melgan_csmsc_ckpt_0.1.1.zip) <br>[mb_melgan_baker_finetune_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/mb_melgan/mb_melgan_baker_finetune_ckpt_0.5.zip)|[mb_melgan_csmsc_static_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/mb_melgan/mb_melgan_csmsc_static_0.1.1.zip) |8.2MB|
 Style MelGAN | CSMSC |[Style MelGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc4)|[style_melgan_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/style_melgan/style_melgan_csmsc_ckpt_0.1.1.zip)| | |
 HiFiGAN | CSMSC |[HiFiGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc5)|[hifigan_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_ckpt_0.1.1.zip)|[hifigan_csmsc_static_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_static_0.1.1.zip)|50MB|
+HiFiGAN | AISHELL-3 |[HiFiGAN-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc5)|[hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip)|||
 WaveRNN | CSMSC |[WaveRNN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc6)|[wavernn_csmsc_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/wavernn/wavernn_csmsc_ckpt_0.2.0.zip)|[wavernn_csmsc_static_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/wavernn/wavernn_csmsc_static_0.2.0.zip)|18MB|


--- a/examples/aishell3/tts3/local/synthesize.sh
+++ b/examples/aishell3/tts3/local/synthesize.sh
@ -4,18 +4,44 @@ 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 ${BIN_DIR}/../synthesize.py \
-    --am=fastspeech2_aishell3 \
-    --am_config=${config_path} \
-    --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
-    --am_stat=dump/train/speech_stats.npy \
-    --voc=pwgan_aishell3 \
-    --voc_config=pwg_aishell3_ckpt_0.5/default.yaml \
-    --voc_ckpt=pwg_aishell3_ckpt_0.5/snapshot_iter_1000000.pdz \
-    --voc_stat=pwg_aishell3_ckpt_0.5/feats_stats.npy \
-    --test_metadata=dump/test/norm/metadata.jsonl \
-    --output_dir=${train_output_path}/test \
-    --phones_dict=dump/phone_id_map.txt \
-    --speaker_dict=dump/speaker_id_map.txt
+stage=0
+stop_stage=0
+
+# pwgan
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize.py \
+        --am=fastspeech2_aishell3 \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=dump/train/speech_stats.npy \
+        --voc=pwgan_aishell3 \
+        --voc_config=pwg_aishell3_ckpt_0.5/default.yaml \
+        --voc_ckpt=pwg_aishell3_ckpt_0.5/snapshot_iter_1000000.pdz \
+        --voc_stat=pwg_aishell3_ckpt_0.5/feats_stats.npy \
+        --test_metadata=dump/test/norm/metadata.jsonl \
+        --output_dir=${train_output_path}/test \
+        --phones_dict=dump/phone_id_map.txt \
+        --speaker_dict=dump/speaker_id_map.txt
+fi
+
+# hifigan
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize.py \
+        --am=fastspeech2_aishell3 \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=dump/train/speech_stats.npy \
+        --voc=hifigan_aishell3 \
+        --voc_config=hifigan_aishell3_ckpt_0.2.0/default.yaml \
+        --voc_ckpt=hifigan_aishell3_ckpt_0.2.0/snapshot_iter_2500000.pd \
+        --voc_stat=hifigan_aishell3_ckpt_0.2.0/feats_stats.npy \
+        --test_metadata=dump/test/norm/metadata.jsonl \
+        --output_dir=${train_output_path}/test \
+        --phones_dict=dump/phone_id_map.txt \
+        --speaker_dict=dump/speaker_id_map.txt
+fi
+
--- a/examples/aishell3/tts3/local/synthesize_e2e.sh
+++ b/examples/aishell3/tts3/local/synthesize_e2e.sh
@ -4,21 +4,50 @@ 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 ${BIN_DIR}/../synthesize_e2e.py \
-    --am=fastspeech2_aishell3 \
-    --am_config=${config_path} \
-    --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
-    --am_stat=dump/train/speech_stats.npy \
-    --voc=pwgan_aishell3 \
-    --voc_config=pwg_aishell3_ckpt_0.5/default.yaml \
-    --voc_ckpt=pwg_aishell3_ckpt_0.5/snapshot_iter_1000000.pdz \
-    --voc_stat=pwg_aishell3_ckpt_0.5/feats_stats.npy \
-    --lang=zh \
-    --text=${BIN_DIR}/../sentences.txt \
-    --output_dir=${train_output_path}/test_e2e \
-    --phones_dict=dump/phone_id_map.txt \
-    --speaker_dict=dump/speaker_id_map.txt \
-    --spk_id=0 \
-    --inference_dir=${train_output_path}/inference
+stage=0
+stop_stage=0
+
+# pwgan
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_aishell3 \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=dump/train/speech_stats.npy \
+        --voc=pwgan_aishell3 \
+        --voc_config=pwg_aishell3_ckpt_0.5/default.yaml \
+        --voc_ckpt=pwg_aishell3_ckpt_0.5/snapshot_iter_1000000.pdz \
+        --voc_stat=pwg_aishell3_ckpt_0.5/feats_stats.npy \
+        --lang=zh \
+        --text=${BIN_DIR}/../sentences.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --phones_dict=dump/phone_id_map.txt \
+        --speaker_dict=dump/speaker_id_map.txt \
+        --spk_id=0 \
+        --inference_dir=${train_output_path}/inference
+fi
+
+# hifigan
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    echo "in hifigan syn_e2e"
+    FLAGS_allocator_strategy=naive_best_fit \
+    FLAGS_fraction_of_gpu_memory_to_use=0.01 \
+    python3 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_aishell3 \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=fastspeech2_nosil_aishell3_ckpt_0.4/speech_stats.npy \
+        --voc=hifigan_aishell3 \
+        --voc_config=hifigan_aishell3_ckpt_0.2.0/default.yaml \
+        --voc_ckpt=hifigan_aishell3_ckpt_0.2.0/snapshot_iter_2500000.pdz \
+        --voc_stat=hifigan_aishell3_ckpt_0.2.0/feats_stats.npy \
+        --lang=zh \
+        --text=${BIN_DIR}/../sentences.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --phones_dict=fastspeech2_nosil_aishell3_ckpt_0.4/phone_id_map.txt \
+        --speaker_dict=fastspeech2_nosil_aishell3_ckpt_0.4/speaker_id_map.txt \
+        --spk_id=0 \
+        --inference_dir=${train_output_path}/inference
+    fi
--- a/examples/aishell3/voc5/README.md
+++ b/examples/aishell3/voc5/README.md
@ -135,8 +135,22 @@ optional arguments:
 3. `--test-metadata` is the metadata of the test dataset. Use the `metadata.jsonl` in the `dev/norm` subfolder from the processed directory.
 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.
-
 ## Pretrained Models
+The pretrained model can be downloaded here [hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip).
+
+
+Model | Step | eval/generator_loss | eval/mel_loss| eval/feature_matching_loss
+:-------------:| :------------:| :-----: | :-----: | :--------:
+default| 1(gpu) x 2500000|24.060|0.1068|7.499
+
+HiFiGAN checkpoint contains files listed below.
+
+```text
+hifigan_aishell3_ckpt_0.2.0
+├── default.yaml                  # default config used to train hifigan
+├── feats_stats.npy               # statistics used to normalize spectrogram when training hifigan
+└── snapshot_iter_2500000.pdz     # generator parameters of hifigan
+```

 ## Acknowledgement
 We adapted some code from https://github.com/kan-bayashi/ParallelWaveGAN.
--- a/paddlespeech/t2s/exps/synthesize.py
+++ b/paddlespeech/t2s/exps/synthesize.py
@ -156,6 +156,7 @@ def parse_args():
        choices=[
            'pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3', 'pwgan_vctk',
            'mb_melgan_csmsc', 'wavernn_csmsc', 'hifigan_csmsc',
+            'hifigan_ljspeech', 'hifigan_aishell3', 'hifigan_vctk',
            'style_melgan_csmsc'
        ],
        help='Choose vocoder type of tts task.')
--- a/paddlespeech/t2s/exps/synthesize_e2e.py
+++ b/paddlespeech/t2s/exps/synthesize_e2e.py
@ -180,9 +180,17 @@ def parse_args():
        type=str,
        default='pwgan_csmsc',
        choices=[
-            'pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3', 'pwgan_vctk',
-            'mb_melgan_csmsc', 'style_melgan_csmsc', 'hifigan_csmsc',
-            'wavernn_csmsc'
+            'pwgan_csmsc',
+            'pwgan_ljspeech',
+            'pwgan_aishell3',
+            'pwgan_vctk',
+            'mb_melgan_csmsc',
+            'style_melgan_csmsc',
+            'hifigan_csmsc',
+            'hifigan_ljspeech',
+            'hifigan_aishell3',
+            'hifigan_vctk',
+            'wavernn_csmsc',
        ],
        help='Choose vocoder type of tts task.')
    parser.add_argument(