matteo-convertino / vosk-build-model
How to create your own model for vosk
β70Updated 3 years ago
Alternatives and similar repositories for vosk-build-model:
Users that are interested in vosk-build-model are comparing it to the libraries listed below
- πΈSTT integration examplesβ126Updated 2 years ago
- Scripts to simplify data prepping for Mozilla DeepSpeech.β14Updated 5 years ago
- Model for recasing and repunctuating ASR transcriptsβ133Updated 11 months ago
- On-device voice activity detection (VAD) powered by deep learningβ202Updated this week
- Kaldi based speaker verificationβ47Updated 7 years ago
- β38Updated 3 years ago
- Linguistic processing for Common Voiceβ55Updated last year
- Speaker diarization python system based on binary key speaker modellingβ61Updated 3 years ago
- Zero-shot multimodal punctuation insertion and truecasing using Whisperβ109Updated 2 years ago
- Adapting your own Language Model for Kaldiβ64Updated 6 years ago
- Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpusβ170Updated 3 months ago
- Rescoring methods for end-to-end Automatic Speech Recognitionβ27Updated 4 years ago
- Improving the Goodness of Pronunciation with DNNs and RNNsβ32Updated 6 years ago
- Grapheme To Phonemeβ70Updated 7 months ago
- scripts to align a given wave to its transcription using trained models by Kaldiβ32Updated 5 years ago
- Goodness of Pronunciation using Kaldi on Epa-DB databaseβ35Updated last year
- An online speech recognition extension toolkit of Kaldiβ56Updated 3 years ago
- Silence detection in audio stream using webrtcvadβ46Updated last year
- Python server for communicating with Kaldi from the browser using WebRTCβ69Updated last year
- Use your data to create a speech recognition system in Kaldi. Fast.β65Updated 5 years ago
- β39Updated last year
- Command line tool to create corpora for Common Voiceβ75Updated 9 months ago
- Reproducible experimental protocols for multimedia (audio, video, text) databaseβ98Updated last month
- A recipe for creating a Speaker Identification system built on Kaldi.β15Updated 5 years ago
- Some simple wrappers around kaldi-asr intended to make using kaldi's (online) decoders as convenient as possible.β170Updated 4 years ago
- Online streaming speaker change detection model in Pytorchβ38Updated last year
- Simplified diarization pipeline using some pretrained models - audio file to diarized segments in a few lines of codeβ145Updated 10 months ago
- Simple Kaldi model server for chain (nnet3) models in online recognition mode directly from a local microphoneβ35Updated 3 years ago
- Speaker diarization based on Kaldi x-vectors, tuned for 16k microphone dataβ96Updated last year
- A better, faster, stronger version of the unbounded interleaved-state recurrent neural network (UIS-RNN)β61Updated 4 years ago