Pinned Loading

1. FireRedTeam/FireRedASR2S FireRedTeam/FireRedASR2S Public

   FireRedASR2S is a SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and singi…

   Python 208 8

2. FireRedTeam/FireRedASR FireRedTeam/FireRedASR Public

   Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics rec…

   Python 1.8k 159

3. Speech-Transformer Speech-Transformer Public

   A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.

   Python 808 196

4. Conv-TasNet Conv-TasNet Public

   A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).

   Python 755 156

5. Listen-Attend-Spell Listen-Attend-Spell Public

   A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.

   Python 205 56

6. TasNet TasNet Public

   A PyTorch implementation of Time-domain Audio Separation Network (TasNet) with Permutation Invariant Training (PIT) for speech separation.

   Python 123 31