diff --git a/demos/speech_server/README.md b/demos/speech_server/README.md index 46d8f7c22cd67e2a51af04e1ccd6d6688c3f2f4c..37a01698773355bda99cc9db64dd0e8068b0009f 100644 --- a/demos/speech_server/README.md +++ b/demos/speech_server/README.md @@ -110,21 +110,22 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee - Python API ```python from paddlespeech.server.bin.paddlespeech_client import ASRClientExecutor + import json asrclient_executor = ASRClientExecutor() - asrclient_executor( + res = asrclient_executor( input="./zh.wav", server_ip="127.0.0.1", port=8090, sample_rate=16000, lang="zh_cn", audio_format="wav") + print(res.json()) ``` Output: ```bash {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'transcription': '我认为跑步最重要的就是给我带来了身体健康'}} - time cost 0.604353 s. ``` ### 5. TTS Client Usage @@ -146,7 +147,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee - `speed`: Audio speed, the value should be set between 0 and 3. Default: 1.0 - `volume`: Audio volume, the value should be set between 0 and 3. Default: 1.0 - `sample_rate`: Sampling rate, choice: [0, 8000, 16000], the default is the same as the model. Default: 0 - - `output`: Output wave filepath. Default: `output.wav`. + - `output`: Output wave filepath. Default: None, which means not to save the audio to the local. Output: ```bash @@ -160,9 +161,10 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee - Python API ```python from paddlespeech.server.bin.paddlespeech_client import TTSClientExecutor + import json ttsclient_executor = TTSClientExecutor() - ttsclient_executor( + res = ttsclient_executor( input="您好，欢迎使用百度飞桨语音合成服务。", server_ip="127.0.0.1", port=8090, @@ -171,6 +173,11 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee volume=1.0, sample_rate=0, output="./output.wav") + + response_dict = res.json() + print(response_dict["message"]) + print("Save synthesized audio successfully on %s." % (response_dict['result']['save_path'])) + print("Audio duration: %f s." %(response_dict['result']['duration'])) ``` Output: @@ -178,7 +185,6 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee {'description': 'success.'} Save synthesized audio successfully on ./output.wav. Audio duration: 3.612500 s. - Response time: 0.388317 s. ``` @@ -211,20 +217,20 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee - Python API ```python from paddlespeech.server.bin.paddlespeech_client import CLSClientExecutor + import json clsclient_executor = CLSClientExecutor() - clsclient_executor( + res = clsclient_executor( input="./zh.wav", server_ip="127.0.0.1", port=8090, topk=1) - + print(res.jaon()) ``` Output: ```bash {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'topk': 1, 'results': [{'class_name': 'Speech', 'prob': 0.9027184844017029}]}} - Response time 0.150897 s. ``` diff --git a/demos/speech_server/README_cn.md b/demos/speech_server/README_cn.md index 1328ca279c99071ac0bcbd3452f61c242a657442..2a18fb40bfa6fbf2b8feab2754731ccf41367981 100644 --- a/demos/speech_server/README_cn.md +++ b/demos/speech_server/README_cn.md @@ -111,21 +111,22 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee - Python API ```python from paddlespeech.server.bin.paddlespeech_client import ASRClientExecutor + import json asrclient_executor = ASRClientExecutor() - asrclient_executor( + res = asrclient_executor( input="./zh.wav", server_ip="127.0.0.1", port=8090, sample_rate=16000, lang="zh_cn", audio_format="wav") + print(res.json()) ``` 输出: ```bash {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'transcription': '我认为跑步最重要的就是给我带来了身体健康'}} - time cost 0.604353 s. ``` @@ -150,7 +151,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee - `speed`: 音频速度，该值应设置在 0 到 3 之间。 默认值：1.0 - `volume`: 音频音量，该值应设置在 0 到 3 之间。 默认值： 1.0 - `sample_rate`: 采样率，可选 [0, 8000, 16000]，默认与模型相同。 默认值：0 - - `output`: 输出音频的路径， 默认值：output.wav。 + - `output`: 输出音频的路径， 默认值：None，表示不保存音频到本地。 输出: ```bash @@ -163,9 +164,10 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee - Python API ```python from paddlespeech.server.bin.paddlespeech_client import TTSClientExecutor + import json ttsclient_executor = TTSClientExecutor() - ttsclient_executor( + res = ttsclient_executor( input="您好，欢迎使用百度飞桨语音合成服务。", server_ip="127.0.0.1", port=8090, @@ -174,6 +176,11 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee volume=1.0, sample_rate=0, output="./output.wav") + + response_dict = res.json() + print(response_dict["message"]) + print("Save synthesized audio successfully on %s." % (response_dict['result']['save_path'])) + print("Audio duration: %f s." %(response_dict['result']['duration'])) ``` 输出: @@ -181,7 +188,6 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee {'description': 'success.'} Save synthesized audio successfully on ./output.wav. Audio duration: 3.612500 s. - Response time: 0.388317 s. ``` @@ -214,20 +220,21 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee - Python API ```python from paddlespeech.server.bin.paddlespeech_client import CLSClientExecutor + import json clsclient_executor = CLSClientExecutor() - clsclient_executor( + res = clsclient_executor( input="./zh.wav", server_ip="127.0.0.1", port=8090, topk=1) + print(res.jaon()) ``` 输出: ```bash {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'topk': 1, 'results': [{'class_name': 'Speech', 'prob': 0.9027184844017029}]}} - Response time 0.150897 s. ``` diff --git a/paddlespeech/server/restful/response.py b/paddlespeech/server/restful/response.py index ce3f34a772f6573e1a2c1520d6eb0f6aacc8a580..a2a207e4f689103c96bd513a8552fcdc3cce24d4 100644 --- a/paddlespeech/server/restful/response.py +++ b/paddlespeech/server/restful/response.py @@ -74,9 +74,11 @@ class TTSResponse(BaseModel): }, "result": { "lang": "zh", - "sample_rate": 24000, + "spk_id": 0, "speed": 1.0, "volume": 1.0, + "sample_rate": 24000, + "duration": 3.6125, "audio": "LTI1OTIuNjI1OTUwMzQsOTk2OS41NDk4...", "save_path": "./tts.wav" }