Merge pull request #1601 from yt605155624/add_ljspeech_hifigan

[TTS] update readme for ljspeech hifigan
3 years ago · 8938483529
parent d48dc8ac63 342b487383
commit 8938483529
7 changed files with 122 additions and 30 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@ -1,4 +1,15 @@
 # Changelog
+
+Date: 2022-3-22, Author: yt605155624.
+Add features to: CLI:
+  - Support aishell3_hifigan、vctk_hifigan
+  - PRLink: https://github.com/PaddlePaddle/PaddleSpeech/pull/1587
+
+Date: 2022-3-09, Author: yt605155624.
+Add features to: T2S:
+  - Add ljspeech hifigan egs.
+  - PRLink: https://github.com/PaddlePaddle/PaddleSpeech/pull/1549
+
 Date: 2022-3-08, Author: yt605155624.
 Add features to: T2S:
  - Add aishell3 hifigan egs.
--- a/docs/source/released_model.md
+++ b/docs/source/released_model.md
@ -54,6 +54,7 @@ Parallel WaveGAN| VCTK |[PWGAN-vctk](https://github.com/PaddlePaddle/PaddleSpeec
 |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 | LJSpeech |[HiFiGAN-ljspeech](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/voc5)|[hifigan_ljspeech_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_ljspeech_ckpt_0.2.0.zip)|||
 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)|||
 HiFiGAN | VCTK |[HiFiGAN-vctk](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/vctk/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/ljspeech/tts3/local/synthesize.sh
+++ b/examples/ljspeech/tts3/local/synthesize.sh
@ -4,17 +4,42 @@ 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 ${BIN_DIR}/../synthesize.py \
-    --am=fastspeech2_ljspeech \
-    --am_config=${config_path} \
-    --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
-    --am_stat=dump/train/speech_stats.npy \
-    --voc=pwgan_ljspeech \
-    --voc_config=pwg_ljspeech_ckpt_0.5/pwg_default.yaml \
-    --voc_ckpt=pwg_ljspeech_ckpt_0.5/pwg_snapshot_iter_400000.pdz  \
-    --voc_stat=pwg_ljspeech_ckpt_0.5/pwg_stats.npy \
-    --test_metadata=dump/test/norm/metadata.jsonl \
-    --output_dir=${train_output_path}/test \
-    --phones_dict=dump/phone_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 ${BIN_DIR}/../synthesize.py \
+        --am=fastspeech2_ljspeech \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=dump/train/speech_stats.npy \
+        --voc=pwgan_ljspeech \
+        --voc_config=pwg_ljspeech_ckpt_0.5/pwg_default.yaml \
+        --voc_ckpt=pwg_ljspeech_ckpt_0.5/pwg_snapshot_iter_400000.pdz  \
+        --voc_stat=pwg_ljspeech_ckpt_0.5/pwg_stats.npy \
+        --test_metadata=dump/test/norm/metadata.jsonl \
+        --output_dir=${train_output_path}/test \
+        --phones_dict=dump/phone_id_map.txt
+fi
+
+# hifigan
+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 ${BIN_DIR}/../synthesize.py \
+        --am=fastspeech2_ljspeech \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=dump/train/speech_stats.npy \
+        --voc=hifigan_ljspeech \
+        --voc_config=hifigan_ljspeech_ckpt_0.2.0/default.yaml \
+        --voc_ckpt=hifigan_ljspeech_ckpt_0.2.0/snapshot_iter_2500000.pdz \
+        --voc_stat=hifigan_ljspeech_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
+fi
+
--- a/examples/ljspeech/tts3/local/synthesize_e2e.sh
+++ b/examples/ljspeech/tts3/local/synthesize_e2e.sh
@ -4,19 +4,45 @@ 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 ${BIN_DIR}/../synthesize_e2e.py \
-    --am=fastspeech2_ljspeech \
-    --am_config=${config_path} \
-    --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
-    --am_stat=dump/train/speech_stats.npy \
-    --voc=pwgan_ljspeech \
-    --voc_config=pwg_ljspeech_ckpt_0.5/pwg_default.yaml \
-    --voc_ckpt=pwg_ljspeech_ckpt_0.5/pwg_snapshot_iter_400000.pdz  \
-    --voc_stat=pwg_ljspeech_ckpt_0.5/pwg_stats.npy \
-    --lang=en \
-    --text=${BIN_DIR}/../sentences_en.txt \
-    --output_dir=${train_output_path}/test_e2e \
-    --inference_dir=${train_output_path}/inference \
-    --phones_dict=dump/phone_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 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_ljspeech \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=dump/train/speech_stats.npy \
+        --voc=pwgan_ljspeech \
+        --voc_config=pwg_ljspeech_ckpt_0.5/pwg_default.yaml \
+        --voc_ckpt=pwg_ljspeech_ckpt_0.5/pwg_snapshot_iter_400000.pdz  \
+        --voc_stat=pwg_ljspeech_ckpt_0.5/pwg_stats.npy \
+        --lang=en \
+        --text=${BIN_DIR}/../sentences_en.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --inference_dir=${train_output_path}/inference \
+        --phones_dict=dump/phone_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 ${BIN_DIR}/../synthesize_e2e.py \
+        --am=fastspeech2_ljspeech \
+        --am_config=${config_path} \
+        --am_ckpt=${train_output_path}/checkpoints/${ckpt_name} \
+        --am_stat=dump/train/speech_stats.npy \
+        --voc=hifigan_ljspeech \
+        --voc_config=hifigan_ljspeech_ckpt_0.2.0/default.yaml \
+        --voc_ckpt=hifigan_ljspeech_ckpt_0.2.0/snapshot_iter_2500000.pdz \
+        --voc_stat=hifigan_ljspeech_ckpt_0.2.0/feats_stats.npy \
+        --lang=en \
+        --text=${BIN_DIR}/../sentences_en.txt \
+        --output_dir=${train_output_path}/test_e2e \
+        --inference_dir=${train_output_path}/inference \
+        --phones_dict=dump/phone_id_map.txt
+fi
--- a/examples/ljspeech/voc5/README.md
+++ b/examples/ljspeech/voc5/README.md
@ -127,6 +127,21 @@ optional arguments:
 5. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.

 ## Pretrained Model
+The pretrained model can be downloaded here [hifigan_ljspeech_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_ljspeech_ckpt_0.2.0.zip).
+
+
+Model | Step | eval/generator_loss | eval/mel_loss| eval/feature_matching_loss
+:-------------:| :------------:| :-----: | :-----: | :--------:
+default| 1(gpu) x 2500000|24.492|0.115|7.227
+
+HiFiGAN checkpoint contains files listed below.
+
+```text
+hifigan_ljspeech_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
--- a/paddlespeech/cli/tts/infer.py
+++ b/paddlespeech/cli/tts/infer.py
@ -237,6 +237,18 @@ pretrained_models = {
        'speech_stats':
        'feats_stats.npy',
    },
+    "hifigan_ljspeech-en": {
+        'url':
+        'https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_ljspeech_ckpt_0.2.0.zip',
+        'md5':
+        '70e9131695decbca06a65fe51ed38a72',
+        'config':
+        'default.yaml',
+        'ckpt':
+        'snapshot_iter_2500000.pdz',
+        'speech_stats':
+        'feats_stats.npy',
+    },
    "hifigan_aishell3-zh": {
        'url':
        'https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip',
@ -389,6 +401,7 @@ class TTSExecutor(BaseExecutor):
                'mb_melgan_csmsc',
                'style_melgan_csmsc',
                'hifigan_csmsc',
+                'hifigan_ljspeech',
                'hifigan_aishell3',
                'hifigan_vctk',
                'wavernn_csmsc',
--- a/tests/unit/cli/test_cli.sh
+++ b/tests/unit/cli/test_cli.sh
@ -21,6 +21,7 @@ paddlespeech tts --voc hifigan_csmsc --input "你好，欢迎使用百度飞桨
 paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0
 paddlespeech tts --am fastspeech2_aishell3 --voc hifigan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0
 paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "Life was like a box of chocolates, you never know what you're gonna get."
+paddlespeech tts --am fastspeech2_ljspeech --voc hifigan_ljspeech --lang en --input "Life was like a box of chocolates, you never know what you're gonna get."
 paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "Life was like a box of chocolates, you never know what you're gonna get." --lang en --spk_id 0
 paddlespeech tts --am fastspeech2_vctk --voc hifigan_vctk --input "Life was like a box of chocolates, you never know what you're gonna get." --lang en --spk_id 0
 paddlespeech tts --am tacotron2_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！"