Search FoxAI

AI Models 535

• whisper-large-v3-turbo-fp16-ov↗

  OpenVINO

• whisper-base-ExecuTorch↗

  software-mansion

• whisper-large-v3-atco2-asr↗

  jlvdoorn

• whisper-tiny_timestamped↗

  onnx-community

  https://huggingface.co/openai/whisper-tiny with ONNX weights to be compatible with Transformers.js. Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

• faster-whisper-large-v3-turbo↗

  h2oai

• whisper-small-cv11-german-ONNX↗

  onnx-community

• whisper-large-v3-turbo↗

  mlx-community

• whisper-large-v3-turbo-hr-parla↗

  GoranS

• CrisperWhisper↗

  nyralabs

  **CrisperWhisper** is an advanced variant of OpenAI's Whisper, designed for fast, precise, and verbatim speech recognition with accurate (**crisp**) word-level timestamps. Unlike the original Whisper, which tends to omit disfluencies and follows more of a intended transcription style, CrisperWhisper aims to transcribe every spoken word exactly as it is, including fillers, pauses, stutters and false starts. Checkout our repo for more details: https://github.com/nyrahealth/CrisperWhisper CrisperWhisper significantly outperforms Whisper Large v3, especially on datasets that have a more verbatim transcription style in the ground truth, such as AMI and TED-LIUM. CrisperWhisper demonstrates superior performance segmentation performance. This performance gap is especially pronounced around disfluencies and pauses. The following table uses the metrics as defined in the paper. For this table we used a collar of 50ms. Heads for each Model were selected using the method described in the How section and the result attaining the highest F1 Score was choosen for each model using varying number of heads.

• whisper-base-ar-quran↗

  tarteel-ai

  This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0839 - Wer: 5.7544 The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - total_train_batch_size: 128 - total_eval_batch_size: 64 - 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 - Transformers 4.26.0.dev0 - Pytorch 1.13.0+cu117 - Datasets 2.7.1.dev0 - Tokenizers 0.13.2