Search FoxAI

AI Models 535

• Breeze-ASR-25↗

  MediaTek-Research

  **Breeze ASR 25** is an advanced ASR model fine-tuned from Whisper-large-v2 - Optimized for Taiwanese Mandarin - Optimized for Mandarin-English code-switching scenarios, including intra-sentential switching and inter-sentential switching. - Enhanced time alignment, suitable for automatic captioning 增強範例-中英混用情境： MediaTek's 24th Anniversary

• whisper-small-uz-v1↗

  OvozifyLabs

• qwen3-tts-12hz-1.7b-ru-stress-cf↗

  siriusfreak

  A fine-tune of Qwen/Qwen3-TTS-12Hz-1.7B-Base that puts Russian word stress where the text marks it — including marks that contradict the dictionary. The mark is the combining acute U+0301 after the stressed vowel: «за́мок» / «замо́к», «сто́ит» / «стои́т», «до́кументы». **Русский.** Дообучение Qwen3-TTS 1.7B: модель ставит ударение туда, где стоит знак U+0301 после ударной гласной, в том числе против словаря. Главное отличие от предыдущих адаптеров — контрафактный штраф при обучении и метки, сверенные со звуком. Ниже — результаты и как обучали. Judged from the audio by a stress detector (see *Evaluation*), 130 sentences, ~730 marks against the dictionary over two sampling seeds, 95% interval ±1.5 points. On ordinary text marked by RUAccent the model departs from the marks in 0.1% of words (voicy 0.6%), with CER 2.9% through Whisper (voicy 4.4%). Homographs (за́мок/замо́к, му́ки/муки́, …) are followed in 98–100% of cases by all fine-tunes, voicy's included.

• Whisper-Hindi2Hinglish-Apex↗

  Oriserve

  1. **Hinglish as a language**: Native ability to transcribe hindi into hinglish, making it easier to understand and process. 2. **Faster Inference**: The model achieves SOTA performance while being upto 8x faster. 3. **Performance Increase**: ~42% average performance increase versus pretrained model across benchmarking datasets. 4. Ranked #1 on Speech-To-Text Arena, beating competitors on transcription preference metric. ***Note***: - *To accurately measure Hinglish transcription performance, the original Hindi ground truth for each dataset was first transliterated to Hinglish. The WER scores below were calculated against this transliterated reference text.* - *To check our model's real-world performance against other SOTA models please head to our Speech-To-Text Arena arena space.* Flash-Attention 2 can be used to make the transcription fast. If your GPU supports Flash-Attention you can use it by, first installing Flash Attention:

• Whisper-Hindi2Hinglish-Swift-ONNX↗

  Hirecentive-D3l

• thewhisper-large-v3↗

  TheStageAI

• whisper-large↗

  OpenAI

  Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need for fine-tuning. Whisper was proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al from OpenAI. The original code repository can be found here. Update: following the release of the paper, the Whisper authors announced a large-v2 model trained for 2.5x more epochs with regularization. This large-v2 model surpasses the performance of the large model, with no architecture changes. Thus, it is recommended that the large-v2 model is used in-place of the original large model.

• faster-whisper-large-v1↗

  Systran

  Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the `compute_type` option in CTranslate2.

• whisper-tamil-small↗

  vasista22

  This model is a fine-tuned version of openai/whisper-small on the Tamil data available from multiple publicly available ASR corpuses. It has been fine-tuned as a part of the Whisper fine-tuning sprint. **NOTE:** The code used to train this model is available for re-use in the whisper-finetune repository. In order to evaluate this model on an entire dataset, the evaluation codes available in the whisper-finetune repository can be used.

• WhisperLv3-FT↗

  inesc-id