voidful / asr-trainer
one script for xls-r/xlsr/whisper fine-tuning
☆41Updated last year
Alternatives and similar repositories for asr-trainer:
Users that are interested in asr-trainer are comparing it to the libraries listed below
- ☆56Updated 2 years ago
- Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together☆47Updated 2 years ago
- 《SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts》☆73Updated last year
- The case study and multilingfual performance of ICASSP submission☆24Updated 2 years ago
- ASR text preprocessing utility☆21Updated 9 months ago
- Putting flows on top of neural transducers for better TTS☆62Updated last month
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated last year
- Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning (ASRU2023)☆27Updated last year
- Open Source Speech/Text Data on AI☆18Updated 2 years ago
- Official release of StyleTalk dataset.☆62Updated 10 months ago
- Official Code for ParrotTTS☆50Updated 6 months ago
- multilingual speech aligner☆74Updated last year
- Taiwanese Speech Synthesis with Tacotron2☆19Updated 2 years ago
- ☆26Updated 3 months ago
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.☆17Updated 5 months ago
- ☆57Updated 10 months ago
- Prosodic Speech Segmentation with Transformers☆25Updated last year
- ☆13Updated 7 months ago
- [IJCAI'23] Learning to Speak from Text for Low-Resource TTS☆63Updated last year
- SpeechGLUE is a speech version of the GLUE benchmark, driven by text-to-speech.☆13Updated last year
- Just another FastSpeech 2 but cleaner code :)☆26Updated 10 months ago
- VoiceBank-2023 is the speech corpus specially designed for constructing personalized Mandarin text-to-speech (TTS) systems.☆39Updated last year
- [ICASSP2023] Source code, model links and open test sets for paper SeACo-Paraformer.☆29Updated last year
- Official code for Interspeech 2023 paper "Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clusterin…☆52Updated last year
- Torchaudio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆11Updated 4 months ago
- Finetuning VITS Efficiently☆32Updated last year
- ☆41Updated last year
- asr2k☆50Updated 11 months ago
- TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loud…☆94Updated 4 months ago
- An audio and transcribed corpus of contemporary Hong Kong Cantonese☆37Updated 4 years ago