wav2vec2

There are 3 repositories under wav2vec2 topic.

• PaddlePaddle / PaddleSpeech

  Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

  asrcode-switchconformerkwspunctuation-restorationself-supervised-learningsound-classificationspeech-alignmentspeech-recognitionspeech-synthesisspeech-translationstreaming-asrstreaming-ttstransformerttsvocodervoice-cloningvoice-recognitionwav2vec2whisper
  Language:Python 10246
• s3prl

  s3prl / s3prl

  Self-Supervised Speech Pre-training and Representation Learning Toolkit

  speech-representationmockingjayrepresentation-learningapcteraself-supervised-learningspeech-pretrainingvq-apcwav2vecvq-wav2vecwav2vec2cpcpasedecoarhubertdistilhubertwavlmunispeech-satdecoar2data2vec
  Language:Python 2111

• audeering / w2v2-how-to

  How to use our public wav2vec2 dimensional emotion model

  speech-emotion-recognitiondeep-learningwav2vec2transformer-modelsarousaldominancevalencemsp-podcastonnx
  Language:Jupyter Notebook 401

• oliverguhr / wav2vec2-live

  A live speech recognition using Facebooks wav2vec 2.0 model.

  speech-recognitionwav2vec2pyaudiowav2vecspeech-to-textasrspeech
  Language:Python 302
• vid2cleantxt

  pszemraj / vid2cleantxt

  Python API & command-line tool to easily transcribe speech-based video files into clean text

  nlpaudioaudio-processingtranscriptionspeech-to-textspeech-recognitionspeechspelling-correctionkeyword-extractionkeywordsentencesentence-boundary-detectionvideo-processingvideotransformerwav2vec2video-summarizationvideo-summarisationpythonwhisper
  Language:Jupyter Notebook 159

• habla-liaa / ser-with-w2v2

  Official implementation of INTERSPEECH 2021 paper 'Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings'

  speech-emotion-recognitionwav2vec2deep-learningtensorflowspeech
  Language:Jupyter Notebook 116

• khanld / ASR-Wav2vec-Finetune

  :zap: Finetune Wa2vec 2.0 For Speech Recognition

  asrpytorchspeech-recognitionwav2vec2finetune-wav2vechuggingfacespeech-to-textvietnamese-speech-recognition
  Language:Python 97

• thevasudevgupta / gsoc-wav2vec2

  GSoC'2021 | TensorFlow implementation of Wav2Vec2

  gsoctensorflowwav2vec2speech-to-textlibrispeech-dataset
  Language:Jupyter Notebook 89
• ASR

  vietai / ASR

  End-to-End Vietnamese Speech Recognition using wav2vec 2.0

  asrasr-modelwav2vec2ctc-losspretrained-weightsend-to-end-speech-recognition
  86

• tuanio / noisy-student-training-asr

  Pytorch implementation of Noisy Student Training for Automatic Speech Recognition and Automatic Pronunciation Error Detection problem

  conformernoisy-studentnstpretrainedpytorchsemi-supervised-learningwav2vec2apeddata-augmentationdeep-learningmachine-learningspeech-recognition
  Language:Python 67

• Telegram-Zalo / zac2022-lyric-alignment

  Solution for Zalo AI Challenge 2022 - Lyrics Alignment

  deep-learningdynamic-programmingforced-alignmentmusic-alignmentpytorchvietnamesewav2vec2
  Language:Python 66

• inboxpraveen / LLM-Minutes-of-Meeting

  🎤📄 An innovative tool that transforms audio or video files into text transcripts and generates concise meeting minutes. Stay organized and efficient in your meetings, and get ready for Phase 2 where we'll be open for contributions to enable real-time meeting transcription! 🚀

  huggingfacehuggingface-transformersllmllm-inferencemeeting-minutesminutes-of-meetingnatural-language-processingnlppythonspeech-recognitionspeech-to-texttransformerstranslationwav2vec2webweb-applicationwebapplicationwhisperwhisper-ai
  Language:CSS 49

• lstrgar / self-supervised-phone-segmentation

  Phoneme segmentation using pre-trained speech models

  hubertspeech-segmentationwav2vec2deep-learningself-supervised-learningspeech-technology
  Language:Python 49
• MiniASR

  vectominist / MiniASR

  A mini, simple, and fast end-to-end automatic speech recognition toolkit.

  asrctcspeech-recognitionspeech-representationwav2vec2hubertminimalpytorchfairseqs3prl
  Language:Jupyter Notebook 48

• mmakiuchi / multimodal_emotion_recognition

  Scripts used in the research described in the paper "Multimodal Emotion Recognition with High-level Speech and Text Features" accepted in the ASRU 2021 conference.

  emotion-recognitionspeech-emotion-recognitiontext-emotion-detectionwav2vec2disentanglement-learningasru2021
  Language:Python 42

• Hamtech-ai / wav2vec2-fa

  fine-tune Wav2vec2. an ASR model released by Facebook

  asr-modelspeech-to-textasrnlphuggingfacetransformerwav2vec2
  Language:Jupyter Notebook 36

• mt-upc / SHAS

  SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

  audio-segmentationspeech-translationspeech-to-textspeechwav2vec2
  Language:Python 34

• pooya-mohammadi / audio-classification-pytorch

  In this project, several approaches for training/finetuning an audio gender recognition is provided. The code can simply be used for any other audio classification task by simply changing the number of classes and the input dataset.

  audio-classificationdeep-learningdeep-utilspythonpytorchlstmtransformerswav2vec2
  Language:Jupyter Notebook 33

• ttop32 / wav2vec2-live-japanese-translator

  real time japanese speech recognition translator using wav2vec2

  speech-to-textautomatic-speech-recognitionasrsttwav2vec2japanesetranslatorpyqt5voice-recognitionvoicereal-timelivehuggingfacepytorchaudiospoken-language-understandingtranslationspeaker-recognitionpyaudiofine-tuning
  Language:Jupyter Notebook 32

• lucasgris / wav2vec4bp

  Wav2vec resources and models for Brazilian Portuguese

  wav2vec2brazilian-portugueseportuguesewav2vecautomatic-speech-recognitiondatasetspeech-to-text
  Language:Jupyter Notebook 31

• ECNU-Cross-Innovation-Lab / ShiftSER

  [ICASSP 2023] Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-trained Representations

  hubertspeech-emotion-recognitionwav2vec2
  Language:Python 29

• egorsmkv / asr-corpus-creator

  This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.

  asraudioaudio-processingautomatic-speech-recognitionnemowav2vec2speech-recognitionwhisper
  Language:Python 27

• khanld / Wav2vec2-Pretraining

  Wav2vec 2.0 Self-Supervised Pretraining

  wav2vec2pretrainingself-supervisedspeech-processingasrcontrastive-learningquantizationspeech-recognitionspeech-to-text
  Language:Python 26

• daanzu / wav2vec2_stt_python

  Simple Python library, distributed via binary wheels with few direct dependencies, for easily using wav2vec 2.0 models for speech recognition

  speech-recognitionspeech-to-textspeechpythonpytorchwav2vec2wav2vec
  Language:Python 23

• AmirAbaskohi / Automatic-Speech-recognition-for-Speech-Assessment-of-Persian-Preschool-Children

  Preschool evaluation is crucial because it gives teachers and parents influential knowledge about children's growth and development. The COVID-19 pandemic has highlighted the necessity of online assessment for preschool children. One of the areas that should be tested is their ability to speak. Employing an Automatic Speech Recognition (ASR) system would not help since they are pre-trained on voices that differ from children's in terms of frequency and amplitude. Because most of these are pre-trained with data in a specific range of amplitude, their objectives do not make them ready for voices in different amplitudes. To overcome this issue, we added a new objective to the masking objective of the Wav2Vec 2.0 model called Random Frequency Pitch (RFP). In addition, we used our newly introduced dataset to fine-tune our model for Meaningless Words (MW) and Rapid Automatic Naming (RAN) tests. Using masking in concatenation with RFP outperforms the masking objective of Wav2Vec 2.0 by reaching a Word Error Rate (WER) of 1.35. Our new approach reaches a WER of 6.45 on the Persian section of the CommonVoice dataset. Furthermore, our novel methodology produces positive outcomes in zero- and few-shot scenarios.

  asrspeech-recognitionwav2vec2datasetdeep-learning
  Language:Jupyter Notebook 20

• hammaad2002 / ASRAdversarialAttacks

  An ASR (Automatic Speech Recognition) adversarial attack repository.

  adversarial-attacksadversarial-machine-learningasrcarlini-wagnercarlini-wagner-attackfgsm-attackhuggingfacehuggingface-libraryhuggingface-transformerhuggingface-transformerspgd-adversarial-attackspgd-attackprojected-gradient-desenttransformerstransformers-librarytransformers-modeltransformers-modelswav2vec2
  Language:Jupyter Notebook 19

• HarunoriKawano / Wav2vec2.0

  Implementation of the paper "wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations" in Pytorch.

  pytorchspeech-recognitionwav2vec2
  Language:Python 19

• yamahigashi / Wav2Vec2FBX

  Recognize speech from an audio file and convert it into animation FBX

  wav2vec2animationlipsyncaudio
  Language:Python 19

• mpoyraz / wav2vec2-turkish

  Turkish Speech Recognition using Facebook's Wav2vec 2.0 models

  speech-recognitionwav2vec2speech-to-textasrturkish
  Language:Python 18
• WOLOF-ASR-Wav2Vec2

  kingabzpro / WOLOF-ASR-Wav2Vec2

  Audio Preprocessing and finetuning of wav2vec2-large-xlsr model on AI4D Baamtu Datamation - Automatic Speech Recognition in WOLOF Data.

  asr-modelwav2vec2wolofafricaaudio-processingaudiofacebooktranscription
  Language:Jupyter Notebook 15

• skit-ai / Map-Mix

  The official implementation of the method discussed in the paper Improving Spoken Language Identification with Map-Mix(work accepted at ICASSP-2023)

  datamapshubertlanguage-identificationmixupspeech-processingspoken-language-identificationspoken-language-recognitionwav2vec2xlsrconfidence-labels
  14
• cantonese-selfish-project

  scottykwok / cantonese-selfish-project

  Cantonese Selfish Project 廣東話自肥企劃 at PYCON HK 2021

  pyconpyconhkcantonesedeepspeechwav2vec2speechrecognitioncantonese-speech-recognition
  Language:Jupyter Notebook 13

• techiaith / docker-huggingface-stt-cy

  Adnabod lleferydd Cymraeg i'r Gymraeg gyda HuggingFace // Speech Recognition for Welsh with HuggingFace

  welshcymraegspeech-recognitionapi-serverwav2vec2speechtraininghuggingfacectc-decodecommonvoice
  Language:Python 13

• JuJu2181 / Automatic-Nepali-Speech-Recognition-and-Summarizer

  A system capable of converting Nepali speech to text and generate summary of text

  abstractive-summarizationdeep-learningextractive-summarizationmachine-learningnepalinepali-nlppythonspeech-recognitionwav2vec2cnn-resnet-bilstmnepali-speechnepali-summary
  Language:Jupyter Notebook 11

• mikezzb / lyrics-sync

  A deep learning lyrics-to-audio alignment system, generating synchronized lyrics from a song and its lyrics

  aideep-learningdemucsjupyter-notebooklyricsmachine-learningmusicmusic-information-retrievalpythonwav2vec2
  Language:Jupyter Notebook 11

• notAI-tech / IndicASR

  Speeech Recognition for Indic languages.

  speech-recognitiontelugutransformerspytorchwav2vecwav2vec2asrindian-languagespeech-to-text
  Language:Python 11