philipperemy/deep-speaker
Deep Speaker: an End-to-End Neural Speaker Embedding System.
This project helps you identify or verify individuals based on their voice. By analyzing short audio clips of speech, it converts voices into unique numerical representations (embeddings). These embeddings can then be compared to determine if two audio samples belong to the same person, or to find a specific speaker within a collection of voices. This is useful for anyone working with voice data, such as security analysts, customer service quality assurance, or researchers in phonetics.
939 stars. No commits in the last 6 months.
Use this if you need to determine if different audio recordings contain the voice of the same individual, or to group audio segments by speaker for tasks like speaker identification or verification.
Not ideal if your audio data is very noisy, contains significant background sound, or includes music, as this can severely impact accuracy.
Stars
939
Forks
238
Language
Python
License
MIT
Category
Last pushed
Apr 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/philipperemy/deep-speaker"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
espnet/espnet
End-to-End Speech Processing Toolkit
yeyupiaoling/PPASR
基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型
yeyupiaoling/PaddlePaddle-DeepSpeech
基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。
flashlight/wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
pannous/tensorflow-speech-recognition
🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks