如何通过JSON创建音频识别转录文本

0

【以下的问题经过翻译处理】我不熟悉JSON文件。对于单个演讲者，我一直在使用Word编辑JSON，因为完整的转录文本可以轻松提取，没有问题。现在对于两个演讲者，我想提取在5000个字符示例文本中显示的语音识别转录文本，其中演讲者已被识别。如何从JSON文件中创建完整转录的语音识别转录文本，就像样本中显示的那样？

Topics

Machine Learning & AI

Tags

Amazon Transcribe

Language

中文 (简体)

EXPERT

rePost Polyglot

asked 8 months ago26 views

1 Answer

Newest
Most votes
Most comments

Are these answers helpful? Upvote the correct answer to help the community benefit from your knowledge.

0

【以下的回答经过翻译处理】我建议您使用或修改下面链接中找到的aws-transcribe-transcript python脚本。该脚本将解析包含多个说话者的json，使其更易读。

链接：https://github.com/trhr/aws-transcribe-transcript

EXPERT

rePost Polyglot

answered 8 months ago

Relevant content

如何讓 IAM 使用者只看的到自己建立的資源 ( How to allow IAM users to only see resources they have created.)
Accepted Answer
kerokero
asked 2 months ago
S3上无法使用Chunked上传文件｜ Unable to use Chunked to upload files on S3
rePost-User-1798329
asked a year ago
sagemaker美国人口普查数据在中国宁夏区下载提示拒绝访问
LiuChuang
asked a year ago
怎样通过CloudFormation来给DocumentDB创建一些表和索引(how to create some table and index in DocumentDB by CloudFormation）
Accepted Answer
Dgk
asked 10 months ago
How do I run Athena queries for pretty-print JSON files?
AWS OFFICIALUpdated a year ago
How do I create complex custom AWS WAF JSON rules?
AWS OFFICIALUpdated 2 years ago
How do I configure an AWS AppSync schema to handle nested JSON data in DynamoDB?
AWS OFFICIALUpdated 2 years ago
Why do I get errors when I try to read JSON data in Amazon Athena?
AWS OFFICIALUpdated 3 months ago
AWS Transfer Family announces structured JSON log format
EXPERT
AWS Transfer Family
published a year ago
How to use the Python json module when decoding DynamoDB items
EXPERT
Brettski-AWS
published 8 months ago