サイト内検索

AI モデル 535

• whisper-kannada-small↗

  vasista22

• Medical-Whisper-Large-v3↗

  Na0s

• faster-whisper-large-v3-turbo-int8↗

  voxta

• whisper-acft↗

  litert-community

• qwen3-forced-aligner-0.6b-GGUF↗

  cstr

  GGUF conversions of `Qwen/Qwen3-ForcedAligner-0.6B` — a single-pass forced aligner that takes any (audio, transcript) pair and predicts per-word/per-token timestamps. Reuses the Qwen3-ASR audio encoder + 28-layer LLM body but swaps the lm_head from `(vocab, d)` to `(5000, d)`: each ` ` placeholder you embed in the input gets a 5000-class softmax over `class * 80 ms` timestamps. Plug it into CrispASR via `-am qwen3-forced-aligner-*.gguf` to get word-level timing on **any** transcription backend — voxtral, voxtral4b, qwen3-asr, granite, parakeet, canary, cohere, even whisper. It's an alternative to the existing `canary-ctc-aligner` second-pass with broader language coverage and 80-ms resolution. The CrispASR C++ runtime auto-detects which variant a loaded GGUF is by reading the lm_head shape from `output.weight.ne[1]` — no separate backend, no separate library.

• faster-whisper-belle-whisper-large-v3-turbo-zh-ct2-int8↗

  wolfofbackstreet

• distil-whisper-large-v3↗

  FL33TW00D-HF

• MiniCPM-o-4_5↗

  openbmb

  A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone > [!NOTE] > [2026.02.06] 🥳 🥳 🥳 We open-sourced a realtime web demo deployable on your own devices like Mac or GPU. Try it now! **MiniCPM-o 4.5** is the latest and most capable model in the MiniCPM-o series. The model is built in an end-to-end fashion based on SigLip2, Whisper-medium, CosyVoice2, and Qwen3-8B with a total of 9B parameters. It exhibits a significant performance improvement, and introduces new features for full-duplex multimodal live streaming. Notable features of MiniCPM-o 4.5 include:

• whisper-base-bungoma.en↗

  eai6

  This model is a fine-tuned version of openai/whisper-base.en on the Azure-dataset dataset. It achieves the following results on the evaluation set: - Loss: 0.0636 - Wer: 25.2804 The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 250 - training_steps: 1000

• whisper-small-egyptian-arabic↗

  MAdel121