speech training recorder下载 - speech training recorder源代码下载

speech training recorder

Ai源码

1.0.0

下载

语音训练记录

简单的GUI应用程序可以帮助记录从给定文本提示的音频，用于培训语音识别或语音综合。

给定一个包含提示的文本文件，此应用程序将选择一个随机选择和订购，显示它们要由用户指示，并分别记录DASTITATION AUDIO和METADATA到.wav文件和recorder.tsv文件。您可以选择以前的录音来播放它，删除并/或重新录制。

要求：

Python 3
请参阅requirements.txt
跨平台：Windows，Linux，MacOS

入门

 git clone https://github.com/daanzu/speech-training-recorder.git
cd speech-training-recorder
mkdir ../audio_data
pip install -r requirements.txt
python3 recorder.py -p prompts/timit.txt

 usage: recorder.py [-h] [-p PROMPTS_FILENAME] [-d SAVE_DIR] [-c PROMPTS_COUNT]
                   [-l PROMPT_LEN_SOFT_MAX] [-o]

Given a text file containing prompts, this app will choose a random selection
and ordering of them, display them to be dictated by the user, and record the
dictation audio and metadata to a `.wav` file and `recorder.tsv` file
respectively.

optional arguments:
  -h, --help            show this help message and exit
  -p PROMPTS_FILENAME, --prompts_filename PROMPTS_FILENAME
                        file containing prompts to choose from
  -d SAVE_DIR, --save_dir SAVE_DIR
                        where to save .wav & recorder.tsv files (default:
                        ../audio_data)
  -c PROMPTS_COUNT, --prompts_count PROMPTS_COUNT
                        number of prompts to select and display (default: 100)
  -l PROMPT_LEN_SOFT_MAX, --prompt_len_soft_max PROMPT_LEN_SOFT_MAX
  -o, --ordered         present prompts in order, as opposed to random
                        (default: False)