FamousDirector / FastWhisper
This is an optimized implementation of OpenAI's Whisper for multilingual transcription.
☆38Updated 2 years ago
Alternatives and similar repositories for FastWhisper:
Users that are interested in FastWhisper are comparing it to the libraries listed below
- Zero-shot multimodal punctuation insertion and truecasing using Whisper☆107Updated 2 years ago
- Putting flows on top of neural transducers for better TTS☆61Updated last week
- ☆38Updated 3 years ago
- ☆69Updated 2 months ago
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GP…☆92Updated 4 months ago
- Speaker change detection using SincNet and an LSTM/Transformer☆46Updated 7 months ago
- Code for our INTERSPEECH paper Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection☆57Updated last month
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.☆15Updated 2 months ago
- Various speech datasets made available to the public☆113Updated 2 months ago
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆74Updated 3 years ago
- ☆21Updated last week
- ASR client for Triton ASR Service☆25Updated 2 months ago
- Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.☆79Updated last year
- Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning (ASRU2023)☆27Updated last year
- Simple voice activity detection (VAD) algorithm in Python☆12Updated last year
- ☆62Updated 9 months ago
- An easy way to fine-tune Wav2Vec 2.0 for low-resource languages.☆81Updated last year
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated last year
- Speech-MASSIVE is a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSI…☆21Updated 5 months ago
- 56 language, 1 model Multilingual ASR☆24Updated 3 years ago
- A Hackable speech recognition library.☆25Updated 4 months ago
- ☆43Updated 2 years ago
- Use quantized versions of Whisper to speed up inference☆12Updated 4 months ago
- Unofficial implementation of miipher☆118Updated 9 months ago
- Grapheme-to-Phoneme transductions that preserve input and output indices, and support cross-lingual g2p!☆147Updated 3 weeks ago
- ☆56Updated 2 years ago
- Finetuning VITS Efficiently☆32Updated last year
- Whisper combined with Silero VAD, for improved long-form transcriptions☆46Updated 2 years ago
- ☆21Updated 5 months ago