Tashkeel-350M-v2 is a model specifically designed for phonetic notation of Arabic text, with 350 million parameters. This model is based on the ibm-granite/granite-4.0-h-350m model and is fine-tuned on the Misraj/Sadeed_Tashkeela dataset. It can automatically add correct phonetic symbols to Arabic text.

Natural Language ProcessingTransformersArabic

This is a model specifically fine-tuned for Lao text summarization tasks. It is based on the Google Gemma 3-12B Instruct model and trained with over 10,000 supervised Lao language samples, capable of generating high-quality Lao text summaries.

Natural Language ProcessingFastaiOther

This is a summary generation model specifically optimized for the Lao language. It is fine-tuned based on the Google Gemma-3-4B-Instruct model and trained with over 5000 high-quality Lao language input-output pairs, mainly focusing on the Artificial Intelligence and Digital Content (AIDC) theme.

Natural Language ProcessingFastaiOther

This model is a fine-tuned model for Japanese phoneme recognition using CTC based on rinna/japanese-hubert-base, which can effectively improve the accuracy of Japanese speech recognition.

Audio ProcessingTransformersJapanese

This is a phoneme transcription model specifically designed for robustly modeling English pronunciation with accents and pronunciation disorders. It uses a vocabulary of 79 symbols in the International Phonetic Alphabet and can predict the phoneme sequence in audio segments, suitable for pronunciation feedback systems and language analysis applications.

Audio ProcessingSafetensorsEnglish

A multimodal speech recognition model optimized for Singapore English, fine-tuned based on Microsoft's Phi-4 multimodal instruction model, significantly improving recognition of Singapore English's unique phonetic features.

MultimodalTransformersMultiple Languages

A named entity recognition model fine-tuned based on DeBERTa, specifically designed to detect personal identifiable information (PII) in text, such as names, social security numbers, phone numbers, and other sensitive information.

Natural Language ProcessingTransformersOther

A BERT-based non-autoregressive Russian grapheme-to-phoneme (G2P) conversion model for predicting phonemes in International Phonetic Alphabet (IPA) format.

Natural Language ProcessingNemoOther

Kokoro is a text-to-speech (TTS) model offering GGUF-encoded versions with dual phonemization support.

Audio ProcessingGguf

A multilingual speech recognition model fine-tuned based on Whisper-base, supporting International Phonetic Alphabet (IPA) output

Audio ProcessingSafetensorsMultiple Languages

A Telugu text-to-speech model fine-tuned based on Microsoft's SpeechT5 architecture, optimized for the unique phoneme structure and text patterns of Telugu.

Audio ProcessingTransformersOther

MiniCPM-V 2.6 is a powerful multimodal large language model that can run efficiently on devices such as mobile phones and supports single-image, multi-image, and video understanding tasks.

MultimodalTransformersOther

A phoneme recognition model fine-tuned based on wav2vec2-base, supporting English speech to International Phonetic Alphabet (IPA) conversion

Audio ProcessingSafetensorsEnglish

A phoneme transcription model fine-tuned on the TIMIT English corpus based on the XLSR pre-trained model, used to convert English audio into phoneme representations.

Audio ProcessingSafetensorsEnglish

A phoneme transcription model fine-tuned on the TIMIT dataset, capable of transcribing English audio into phoneme representations

Audio ProcessingSafetensorsEnglish

A Thai sentiment analysis model fine-tuned based on the WangchanBERTa model, used to analyze the emotional tendency of Thai text.

Natural Language ProcessingTransformersOther

This is a model specifically designed to detect personal data in documents. It can identify 12 common types of personal sensitive information, including names, addresses, phone numbers, ID card numbers, etc., to help users protect data privacy and conduct security reviews.

Natural Language ProcessingTransformers

An automatic speech recognition model based on Wav2Vec2-Base architecture, specifically fine-tuned for phoneme recognition on the LJSpeech Phonemes dataset

Audio ProcessingTransformersEnglish

A chat model fine-tuned by H2O.ai with 4 billion parameters, supporting text generation tasks and capable of offline operation on mobile phones.

Natural Language ProcessingTransformersEnglish

A speech recognition model fine-tuned on the TIMIT dataset based on facebook/wav2vec2-large-lv60, focusing on the phoneme recognition task.

Audio ProcessingTransformersEnglish