Downloads · 30 days
10
13% of all-time downloads
todo1111/lfm2-5-audio-jp-ss-jdsc-asr-concat-tts-v1
lfm2-5-audio-jp-ss-jdsc-asr-concat-tts-v1 is a automatic speech recognition model from todo1111. Use it when you need speech turned into text. It is set up for liquid-audio. The card lists the license as other.
Fine-tuned LiquidAI/LFM2.5-Audio-1.5B-JP for Japanese dysarthric ASR on SS-JDSC.
Downloads · 30 days
10
13% of all-time downloads
All-time downloads
80
Public
Parameters
1.5B
3.6 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors3.6 GB · 100%
How the weights are stored.
BF161.5B · 100%
From the Hugging Face model README
Fine-tuned LiquidAI/LFM2.5-Audio-1.5B-JP for Japanese dysarthric ASR on SS-JDSC.
LiquidAI/LFM2.5-Audio-1.5B-JPasr_ft_concat_tts_v1Perform ASR in Japanese.ss-jdsc-asrThis repo contains the fine-tuned Liquid Audio checkpoint files copied from:
/vol/ss_jdsc/checkpoints/asr_ft_concat_tts_v1/final
Evaluation artifacts are included under eval/asr_ft_concat_tts_v1/ when available.