Joh Bo's picture

4

Joh Bo PRO

johnnyb0y

·

johnny-boufarhat-09967714a

AI & ML interests

None yet

Recent Activity

reacted to YatharthS's post with 🔥 about 1 month ago

Just released a heavily optimized library for NeuTTS. It's over 200x realtime meaning it can generate over 200 seconds of audio in a single second using batching and supports voice cloning!!🤯🤯 Link: https://github.com/ysharma3501/FastNeuTTS

liked a model 3 months ago

internlm/Spark-VL-7B

replied to ACloudCenter's post 4 months ago

I've really been into testing the various ASR, TTS, and other audio related models. This space showcases the Nvidia Canary-Qwen 2.5B model. The model is able to transcribe incredibly fast and and combine qwen for queries about the transcript. All audio example files were generated with my adjacent VibeVoice Conference Generator Space. Another really cool model!! https://huggingface.co/spaces/ACloudCenter/canary-qwen-transcriber-2.5b

View all activity

Organizations

None yet

reacted to YatharthS's post with 🔥 about 1 month ago

Post

1403

Just released a heavily optimized library for NeuTTS. It's over 200x realtime meaning it can generate over 200 seconds of audio in a single second using batching and supports voice cloning!!🤯🤯

Link: https://github.com/ysharma3501/FastNeuTTS

liked a model 3 months ago

internlm/Spark-VL-7B

Video-Text-to-Text • 8B • Updated Oct 23 • 53 • 10

replied to ACloudCenter's post 4 months ago

Hey! Would love to chat with you about this and the speech work you're doing! ( my LI in profile or lmk where to email you

liked 3 models 7 months ago

Motif-Technologies/Motif-2.6B

Text Generation • 3B • Updated Aug 28 • 241 • 78

Hcompany/Holo1-7B

Image-Text-to-Text • 8B • Updated Jun 10 • 289 • 224

ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition

Audio Classification • 0.3B • Updated Oct 24, 2024 • 52.6k • 237