LibriSpeech-PC
Emerging5papers using it
2023first seen
Merge Librispeech audio files with punctuation and captalization restored transcripts from LibriSpeech-PC. I refered to the original LibriSpeech dataset module script from HuggingFace Datasets (https://huggingface.co/datasets/openslr/librispeech_asr). If you already have downloaded the LibriSpeech dataset via `load_dat
Papers using LibriSpeech-PC (5)
- Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech SynthesisContinuous-Token Diffusion for Speaker-Referenced TTS in Multimodal LLMsPoDAR: Power-Disentangled Audio Representation for Generative ModelingARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated InferenceLibriSpeech-PC: Benchmark for Evaluation of Punctuation and
Capitalization Capabilities of end-to-end ASR Models