From dcb42cb66c1f8d017cc7f11ccbe8d637b96f3159 Mon Sep 17 00:00:00 2001 From: WongLaw Date: Wed, 14 Sep 2022 06:59:41 +0000 Subject: [PATCH] Removed useless spk_id in speech_server and streaming_tts_server from demos, and support bilingual server engine. --- demos/speech_server/conf/application.yaml | 4 ++-- demos/streaming_tts_server/conf/tts_online_application.yaml | 2 +- .../streaming_tts_server/conf/tts_online_ws_application.yaml | 2 +- paddlespeech/server/engine/engine_warmup.py | 4 +++- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/demos/speech_server/conf/application.yaml b/demos/speech_server/conf/application.yaml index 9c171c470..b5ee80095 100644 --- a/demos/speech_server/conf/application.yaml +++ b/demos/speech_server/conf/application.yaml @@ -61,7 +61,7 @@ tts_python: phones_dict: tones_dict: speaker_dict: - spk_id: 0 + # voc (vocoder) choices=['pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3', # 'pwgan_vctk', 'mb_melgan_csmsc', 'style_melgan_csmsc', @@ -87,7 +87,7 @@ tts_inference: phones_dict: tones_dict: speaker_dict: - spk_id: 0 + am_predictor_conf: device: # set 'gpu:id' or 'cpu' diff --git a/demos/streaming_tts_server/conf/tts_online_application.yaml b/demos/streaming_tts_server/conf/tts_online_application.yaml index e617912fe..04fb080b8 100644 --- a/demos/streaming_tts_server/conf/tts_online_application.yaml +++ b/demos/streaming_tts_server/conf/tts_online_application.yaml @@ -29,7 +29,7 @@ tts_online: phones_dict: tones_dict: speaker_dict: - spk_id: 0 + # voc (vocoder) choices=['mb_melgan_csmsc, hifigan_csmsc'] # Both mb_melgan_csmsc and hifigan_csmsc support streaming voc inference diff --git a/demos/streaming_tts_server/conf/tts_online_ws_application.yaml b/demos/streaming_tts_server/conf/tts_online_ws_application.yaml index 329f882cc..a5abcde39 100644 --- a/demos/streaming_tts_server/conf/tts_online_ws_application.yaml +++ b/demos/streaming_tts_server/conf/tts_online_ws_application.yaml @@ -29,7 +29,7 @@ tts_online: phones_dict: tones_dict: speaker_dict: - spk_id: 0 + # voc (vocoder) choices=['mb_melgan_csmsc, hifigan_csmsc'] # Both mb_melgan_csmsc and hifigan_csmsc support streaming voc inference diff --git a/paddlespeech/server/engine/engine_warmup.py b/paddlespeech/server/engine/engine_warmup.py index 3751554c2..ff65dff97 100644 --- a/paddlespeech/server/engine/engine_warmup.py +++ b/paddlespeech/server/engine/engine_warmup.py @@ -27,8 +27,10 @@ def warm_up(engine_and_type: str, warm_up_time: int=3) -> bool: sentence = "您好，欢迎使用语音合成服务。" elif tts_engine.lang == 'en': sentence = "Hello and welcome to the speech synthesis service." + elif tts_engine.lang == 'mix': + sentence = "您好，欢迎使用TTS多语种服务。" else: - logger.error("tts engine only support lang: zh or en.") + logger.error("tts engine only support lang: zh or en or mix.") sys.exit(-1) if engine_and_type == "tts_python":