Quantized GGUF versions of LiquidAI’s LFM 2.5‑Audio 1.5B JP model, including language, audio encoder, and vocoder weights (F32/F16/Q8_0/Q4_0), plus CLI/Server runners for ASR and TTS with llama.cpp.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
506,000
Hugging Face likes
37
Listed
Jun 15, 2026
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | — |
| Jan 2026 | — |
| Feb 2026 | — |
| Mar 2026 | — |
| Apr 2026 | — |
| May 2026 | — |
| Jun 2026 | 5,000 |
| Jul 2026 | 2,000 |
| Aug 2026 | 2,000 |
| Sep 2026 | 3,000 |
| Oct 2026 | 280,000 |
| Nov 2026 | 506,000 |
Downloads over the 30 days before the last snapshot of each month.
Resources in similar research fields
- piper-plus-tsukuyomi-chanayousanz4kA Japanese TTS model named tsukuyomi‑wavlm—fine‑tuned for 300 epochs on 100 utterances from the tsukuyomi corpus, using the WavLM discriminator and A1/A2/A3 prosody features on a VITS architecture, exported as a 61 MB ONNX file that generates 22.05 kHz syntheses.Shared: Speech & Audio in NLP
- sarashina2.2-ttssbintuitions3kA Japanese‑centric, bilingual text‑to‑speech system built on a large language model that delivers highly accurate, natural, and stable pronunciation for both Japanese and English—including mixed code‑switching—and supports zero‑shot voice cloning across diverse speaking styles with responsibly sourced training data.Shared: Speech & Audio in NLP
- japanese-hubert-base-phoneme-ctcprj-beatrice4kFine‑tuned Japanese phoneme CTC model based on rinna/japanese‑hubert‑base, trained with ReazonSpeech v2 data and pyopenjtalk‑plus labels, achieving improved accuracy in a new v2 release (prj-beatrice/japanese-hubert-base-phoneme-ctc-v2).Shared: Speech & Audio in NLP
- japanese-hubert-base-phoneme-ctc-v3prj-beatrice2kFine‑tuned Japanese HuBERT‑base for CTC phoneme recognition (v3), adding MeCab N‑best with pyopenjtalk‑plus post‑processing, a weighted loss combining CTC and MeCab costs, updated exclusion rules, and a new “ty” phoneme.Shared: Speech & Audio in NLP
- wav2vec2-large-xlsr-japanese-hiraganavumichien153kA Japanese speech‑recognition model fine‑tuned from facebook/wav2vec2‑large‑xlsr‑53 on Common Voice and the JSUT corpus, optimized for 16 kHz audio input.Shared: Speech & Audio in NLP
voicevox_engineVOICEVOX1.8kVOICEVOX is a high-quality text-to-speech software that can be used for free.GitHubShared: Speech & Audio in NLP