Bhavik B Vachhani

bbvachhani's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model 15 days ago

google/medasr

Automatic Speech Recognition • Updated 17 days ago • 4.93k • 197

liked a Space about 1 month ago

Running

18

The SpeechLLM Playbook

🔊

18

🚧 [WiP] A deepdive into SpeechLLMs and Neural Audio Codec

liked a model about 1 month ago

sesame/csm-1b

Text-to-Speech • Updated Dec 1, 2025 • 24.9k • 2.31k

liked a Space about 2 months ago

Running

53

MEDIC Benchmark

📊

53

View and compare medical LLM evaluations

liked a model about 2 months ago

MahmoudAshraf/mms-300m-1130-forced-aligner

Automatic Speech Recognition • 0.3B • Updated Sep 28, 2024 • 2.96M • 69

liked a model 2 months ago

google/gemma-3n-E2B-it

Image-Text-to-Text • 5B • Updated Jul 14, 2025 • 197k • 246

liked a Space 4 months ago

Sleeping

4

Causal Whisper Streaming

🎤

4

Start recording to transcribe speech in real-time

liked a model 4 months ago

nvidia/diar_streaming_sortformer_4spk-v2

Automatic Speech Recognition • Updated 8 days ago • 8.57k • 91

liked a model 5 months ago

HPAI-BSC/Qwen2.5-Aloe-Beta-7B

Question Answering • 8B • Updated Oct 24, 2025 • 320 • 10

liked 4 Spaces 5 months ago

Running

Featured

168

Appoint Ready - MedGemma Demo

📋

168

Simulated Pre-visit Intake Demo built using MedGemma

Running

64

RadExtract

🗂

64

Transform unstructured radiology reports into structured data

Running

4

How Biased is Whisper?

🤫

4

Display and filter Whisper model evaluation results

Running

27

Hebrew Transcription Leaderboard

🥇

27

Benchmarking Hebrew Speech-to-Text Models

liked a model 5 months ago

fixie-ai/ultravox-v0_5-llama-3_1-8b

Audio-Text-to-Text • 0.7B • Updated May 6, 2025 • 2.51k • 34

liked a Space 5 months ago

Running

10

Open Universal Arabic Asr Leaderboard

🥇

10

A benchmark for open-source multi-dialect Arabic ASR models

liked a model 5 months ago

PRAli22/arabert_arabic_ner

Token Classification • 0.1B • Updated Mar 7, 2024 • 4 • 1

liked 2 Spaces 6 months ago

Running on CPU Upgrade

Featured

1.18k

Open ASR Leaderboard

🏆

1.18k

View and request speech models benchmark data

Running

64

Open Universal Arabic Asr Leaderboard

🥇

64

A benchmark for open-source multi-dialect Arabic ASR models

liked 2 models 6 months ago

aubmindlab/bert-base-arabertv2

Fill-Mask • 0.1B • Updated Aug 3, 2023 • 88.7k • • 41

nvidia/stt_ar_fastconformer_hybrid_large_pc_v1.0

Automatic Speech Recognition • Updated Oct 23, 2025 • 662 • 12