サイト内検索

AI モデル 84759

• mms-tts-nlg↗

  facebook

• mms-tts-srn↗

  facebook

• MobileLLM-ParetoQ-600M-1-bit↗

  facebook

• vibert-base-cased↗

  FPTAI

• ind-100mb-after-wc-zipf-newlex-before-ckpt500-packed-bfdiso_seed455↗

  francesca9805

• gemma-9b-rm-domain-c1.5-c2.0-m1.0-sr1.0-sp1.0-n0-a350↗

  georgeyw

• DeepSeek-V4.1-Flash-4bit-paged↗

  GreenBitAI

• qwen2.5-0.5b-acelog-json↗

  grendo55

• chinese-llama-2-7b-64k-gguf↗

  hfl

• Zipformer-30M-RNNT-6000h↗

  hynt

  The **Vietnamese Speech-to-Text (ASR)** model is built on the **ZipFormer architecture** — an improved variant of the Conformer — featuring only **30 million parameters** yet achieving **exceptional performance** in both speed and accuracy. On CPU, the model can transcribe a **12-second audio clip in just 0.3 seconds**, significantly faster than most traditional ASR systems without requiring a GPU. This model was trained entirely on **self-funded, personal hardware** — every GPU hour and electricity bill came out of my own pocket. If this work is useful to you, a small contribution helps cover the cost of the next training run and keeps future models free and open. Every coffee is hugely appreciated 🙏 You can try the model directly here: 👉 https://huggingface.co/spaces/hynt/k2-automatic-speech-recognition-demo