Search FoxAI

AI Models 535

• higgs-audio-v3-8b-stt-v2↗

  bosonai

  A speech-to-text model combining a Whisper-Large-v3 encoder with a Qwen3-8B decoder (8.91B total parameters), fine-tuned with LoRA on diverse ASR benchmarks.

• whisper-large-v2-formosan-lang-tokens-ct2↗

  ILRDF

• whisper-tamil-medium↗

  vasista22

• whisper-small-int8-ov↗

  OpenVINO

• whisper-medium.en-mlx↗

  mlx-community

• whisper-turbo-v3-urdu↗

  awaaz-se-alfaaz

• owsm_ctc_v4_1B↗

  espnet

  Open Whisper-style Speech Model (OWSM) is the first **fully open** Whisper-style speech foundation model. It reproduces and advances OpenAI's Whisper-style training using publicly available data and open-source toolkits. The code, pre-trained model weights, and training logs are publicly released to promote open science in speech foundation models. OWSM-CTC (Peng et al., ACL 2024) is a novel encoder-only speech foundation model based on hierarchical multi-task self-conditioned CTC. It supports multilingual speech recognition, speech translation, and language identification within a single non-autoregressive model. OWSM-CTC v4 is trained for three epochs on 320k hours of public audio data covering multilingual speech recognition, any-to-any speech translation, and language identification. The newly curated data are publicly released: https://huggingface.co/datasets/espnet/yodas_owsmv4

• whisper-large-v3-gguf↗

  vonjack

• whisper-tiny-ar-quran↗

  tarteel-ai

  This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0928 - Wer: 7.0535 The following hyperparameters were used during training: - learning_rate: 0.0001 - 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: 500 - training_steps: 5000 - mixed_precision_training: Native AMP

• stream-1-mini↗

  whisperstream