正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

LETS GOO! Parler TTS 🔥 A fully open-source, Apache 2.0 licensed Text-to-speech model focused on providing maximum controllability. Through voice prompts, you can control the pitch, speed, gender, noise levels, emotion characteristics and more! > Trained on 10K hours of permissive data. > Offers control over the generations. >... show more

Vaibhav (VB) Srivastav

41,658 subscribers

156,386 次观看 • 2 年前 •via X (Twitter)

教育健康养生科学技术

Anya Rossi• Live Now

Private livecam show

9 条评论

Vaibhav (VB) Srivastav 的头像

Vaibhav (VB) Srivastav2 年前

Try it out in the space directly (& share your generations below)!

Vaibhav (VB) Srivastav 的头像

Vaibhav (VB) Srivastav2 年前

Check out our inference plus training code base here:

Vaibhav (VB) Srivastav 的头像

Vaibhav (VB) Srivastav2 年前

You should also be able to use it in a Colab with less than 10 lines of code: import torch from parler_tts import ParlerTTSForConditionalGeneration from transformers import AutoTokenizer import soundfile as sf device = "cuda:0" if torch. cuda. is_available() else "cpu" model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler_tts_mini_v0.1").to(device) tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler_tts_mini_v0.1") prompt = "Hey, how are you doing today?" description = "A female speaker with a slightly low-pitched voice delivers her words quite expressively, in a very confined sounding environment with clear audio quality." input_ids = tokenizer(description, return_tensors="pt").input_ids.to(device) prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device) generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids) audio_arr = generation.cpu().numpy().squeeze() sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)

Dennis Lysenko 的头像

Dennis Lysenko2 年前

@reach_vb this is awesome -- can we run this on Replicate?

Vaibhav (VB) Srivastav 的头像

Vaibhav (VB) Srivastav2 年前

Not yet, but you can try it out and use it here:

Javier de la Rosa @versae@mastodon.social 的头像

Javier de la Rosa @[email protected]2 年前

This is really cool! I've been looking at Parler and Data-Speech and would love to give it a try for low-resource languages. What's the minimum amount of hours needed for this to adapt to another language? And does the audio need to be separated by speaker?

Vaibhav (VB) Srivastav 的头像

Vaibhav (VB) Srivastav2 年前

We will release fine-tuning support soon. I think for the most part the quality of the dataset matters way more than the quantity. You’d need to have enough diversity to ensure a balance in the voice prompts. Once that is in you should be able to train in any language. That said, we haven’t tried this yet, so this is all a hypothesis at this point.

bitBrain 的头像

bitBrain2 年前

@ClementDelangue but can it laugh? nono sorry, I mean Holy shit! nice!

bane 的头像

bane2 年前

@huggingface Not bad

相关视频

Introducing Indic-Parler TTS - Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! 🔥 A collaboration w/ AI4Bharat & Hugging Face - w/ fully customisable speech and voice personas! Try it out directly below or use the model weights as you want! 🇮🇳/acc

Introducing Indic-Parler TTS - Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! 🔥 A collaboration w/ AI4Bharat & Hugging Face - w/ fully customisable speech and voice personas! Try it out directly below or use the model weights as you want! 🇮🇳/acc

Vaibhav (VB) Srivastav

42,184 次观看 • 1 年前

LETS GOOO! FishSpeech v1.5 - multilingual, zero-shot instant voice cloning, low-latency, open text to speech model 🔥 > Only 500M params > Trained on 1 MILLION hours of audio > Supports 13 languages > Low-latency ( Open model - checkpoints on the hub 🤗 > Best part: Ranks #2 on TTS Arena (preliminary results) Kudos to Fish Audio - truly leading the way for open text to speech research! ⚡

LETS GOOO! FishSpeech v1.5 - multilingual, zero-shot instant voice cloning, low-latency, open text to speech model 🔥 > Only 500M params > Trained on 1 MILLION hours of audio > Supports 13 languages > Low-latency ( Open model - checkpoints on the hub 🤗 > Best part: Ranks #2 on TTS Arena (preliminary results) Kudos to Fish Audio - truly leading the way for open text to speech research! ⚡

Vaibhav (VB) Srivastav

49,141 次观看 • 1 年前

The largest fully annotated open egocentric human dataset. Today we're open-sourcing EgoSuite-Open100K with Hugging Face : 100,000 hours of egocentric human data, free for anyone to use. Physical AI has a scaling law of its own now, and its input is human data. That part is settled. What the field still needs is a shared foundation to build on. 15,000+ tasks. 15,000+ real scenes, from factory floors to retail backrooms. Hand pose, body pose and subtask-level semantics, with wrist camera coverage on part of the set. Licensed for commercial training, not research-only. We build the data infrastructure for Physical AI. Open100K is the first public layer of it. The first 10,000 hours are live now, with the rest rolling out in stages.

The largest fully annotated open egocentric human dataset. Today we're open-sourcing EgoSuite-Open100K with Hugging Face : 100,000 hours of egocentric human data, free for anyone to use. Physical AI has a scaling law of its own now, and its input is human data. That part is settled. What the field still needs is a shared foundation to build on. 15,000+ tasks. 15,000+ real scenes, from factory floors to retail backrooms. Hand pose, body pose and subtask-level semantics, with wrist camera coverage on part of the set. Licensed for commercial training, not research-only. We build the data infrastructure for Physical AI. Open100K is the first public layer of it. The first 10,000 hours are live now, with the rest rolling out in stages.

Lightwheel

73,314 次观看 • 18 天前

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Base Labs

210,723 次观看 • 5 天前

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

kwindla

42,246 次观看 • 1 年前

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses three NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

kwindla

274,679 次观看 • 8 个月前

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:

AI4Bharat

28,681 次观看 • 1 年前

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗

Vaibhav (VB) Srivastav

299,066 次观看 • 1 年前

This giant free dataset could make helper robots way smarter, way faster: An open-source robotics stack from Berkeley AI researchers featuring the largest teleoperation dataset released to date with over 3,500 hours of bimanual manipulation data across 200 tasks. The video showcases autonomous bimanual robot performance on dexterous tasks including box folding, Lego sorting, AirPod insertion, t-shirt folding, backpack packing, and box unlocking using learned policies. Sim-to-real correlations, training insights like flow loss predicting real-world success, lightweight infrastructure for DAgger interventions Thank you for sharing, Ritvik Singh, and everyone else who contributed to this! Links to the paper plus dataset at under permissive licensing. ——- Weekly robotics and AI insights. Subscribe free:

This giant free dataset could make helper robots way smarter, way faster: An open-source robotics stack from Berkeley AI researchers featuring the largest teleoperation dataset released to date with over 3,500 hours of bimanual manipulation data across 200 tasks. The video showcases autonomous bimanual robot performance on dexterous tasks including box folding, Lego sorting, AirPod insertion, t-shirt folding, backpack packing, and box unlocking using learned policies. Sim-to-real correlations, training insights like flow loss predicting real-world success, lightweight infrastructure for DAgger interventions Thank you for sharing, Ritvik Singh, and everyone else who contributed to this! Links to the paper plus dataset at under permissive licensing. ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

13,264 次观看 • 2 个月前

100,000 hours of human hands doing real work. LeRobot format, fully annotated and open. EgoSuite-Open100K from Lightwheel X Hugging Face: 15,000+ tasks across 15,000+ real scenes, hand + body pose and wrist cams. Recorded across 7 environment categories and 128 scene types, from kitchens and bedrooms to warehouse floors and assembly lines. It's open for academic research and commercial training, and streams straight from the Hub. Always great to see a dataset at this scale released openly on the Hub. More info:

100,000 hours of human hands doing real work. LeRobot format, fully annotated and open. EgoSuite-Open100K from Lightwheel X Hugging Face: 15,000+ tasks across 15,000+ real scenes, hand + body pose and wrist cams. Recorded across 7 environment categories and 128 scene types, from kitchens and bedrooms to warehouse floors and assembly lines. It's open for academic research and commercial training, and streams straight from the Hub. Always great to see a dataset at this scale released openly on the Hub. More info:

LeRobot

44,777 次观看 • 18 天前

Can 1,000 real-world 3D scenes make a state-of-the-art model better? At OVER Research, we tested it by fine-tuning R3, a state-of-the-art streaming 3D reconstruction model, on roughly 1,000 scenes from the OVER dataset. The result: 25% lower trajectory error on our real-world environments compared to the deployed public checkpoint. And we did it using only 1,000 scenes, the same open dataset anyone can download for free, out of the 285,000+ real-world 3D scenes OVER has today. Read the full OVER Research publication: Download the 1,000-scene dataset on Hugging Face:

Can 1,000 real-world 3D scenes make a state-of-the-art model better? At OVER Research, we tested it by fine-tuning R3, a state-of-the-art streaming 3D reconstruction model, on roughly 1,000 scenes from the OVER dataset. The result: 25% lower trajectory error on our real-world environments compared to the deployed public checkpoint. And we did it using only 1,000 scenes, the same open dataset anyone can download for free, out of the 285,000+ real-world 3D scenes OVER has today. Read the full OVER Research publication: Download the 1,000-scene dataset on Hugging Face:

Over the Reality 🌐

34,492 次观看 • 15 天前

Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches compromise the expressive aspects of speech. Using phonetic, pitch and tone tokens, Spirit LM models can overcome these limitations for both inputs and outputs to generate more natural sounding speech while also learning new tasks across ASR, TTS and speech classification. We hope that sharing this work will enable the research community to further new approaches for text and speech integration.

Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches compromise the expressive aspects of speech. Using phonetic, pitch and tone tokens, Spirit LM models can overcome these limitations for both inputs and outputs to generate more natural sounding speech while also learning new tasks across ASR, TTS and speech classification. We hope that sharing this work will enable the research community to further new approaches for text and speech integration.

AI at Meta

351,764 次观看 • 1 年前

LegoGPT, an LLM-based system that generates physically stable LEGO structures from text prompts, backed by a new 47,000+ sample dataset and physics-aware filtering during inference. → LegoGPT is trained on a custom dataset, StableText2Lego, which includes 47,000+ 3D LEGO models mapped to text, spanning 28,000+ unique objects. → The model predicts LEGO bricks sequentially like tokens, using next-token prediction in a transformer setup. → To ensure physical stability, LegoGPT integrates physics-aware rollback and validity filtering, pruning out structurally invalid brick placements. → The generated designs are aesthetically aligned with prompts, physically buildable, and tested both with human manual assembly and robotic arms. → The team also introduced a text-driven LEGO coloring/texturing pipeline, enabling more expressive and customized outputs. → The dataset, code, and models are all publicly released under an open-access license.

LegoGPT, an LLM-based system that generates physically stable LEGO structures from text prompts, backed by a new 47,000+ sample dataset and physics-aware filtering during inference. → LegoGPT is trained on a custom dataset, StableText2Lego, which includes 47,000+ 3D LEGO models mapped to text, spanning 28,000+ unique objects. → The model predicts LEGO bricks sequentially like tokens, using next-token prediction in a transformer setup. → To ensure physical stability, LegoGPT integrates physics-aware rollback and validity filtering, pruning out structurally invalid brick placements. → The generated designs are aesthetically aligned with prompts, physically buildable, and tested both with human manual assembly and robotic arms. → The team also introduced a text-driven LEGO coloring/texturing pipeline, enabling more expressive and customized outputs. → The dataset, code, and models are all publicly released under an open-access license.

Rohan Paul

75,281 次观看 • 1 年前

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

Vaibhav (VB) Srivastav

79,645 次观看 • 1 年前

VoxCPM 2 just dropped by OpenBMB Only 2B-param open-source TTS (Text-to-Speech) model built for production-grade multilingual voice work. Apache-2.0 license, Can run on only 8GB VRAM. • Eliminates the "robotic" feel of traditional TTS, delivering prosody and emotional depth suitable for high-stakes professional environments like filmmaking, gaming, animation, and audiobooks. • 30-language multilingual: no language tag needed, just type in a supported language and generate directly. • Voice design: create a brand-new voice from a text description alone, like age, tone, pace, or emotion. No reference audio required. Describe the desired voice characteristics (gender, age, tone, emotion, pace …) in Control Instruction, and VoxCPM2 will craft a unique voice from your description alone. • Controllable cloning: clone from a short clip, then steer delivery style without losing the speaker’s core voice. • Ultimate cloning: use reference audio + transcript for continuation-style cloning that keeps the tiny vocal details. • 48kHz output: takes 16kHz reference audio and produces studio-quality speech without an external upsampler. • Real-time ready: around 0.3 RTF on RTX 4090, even lower with Nano-VLLM. • Commercial use: Apache-2.0 licensed. Developer-Friendly Infrastructure: - Native Torch Inference: Direct support for PyTorch-based workflows. - Training Flexibility: Supports both full-parameter and LoRA fine-tuning for specific domain adaptation. - Production Readiness: Compatible with voxcpm-nanovllm for large-scale, high-concurrency deployment.

Rohan Paul

13,541 次观看 • 4 个月前

If you're looking for a weekend project, how about training your own text-to-speech model from scratch on your own GPU, and then running it on any device's CPU? We just open-sourced the entire Pocket TTS training stack: data pipeline, recipes, and evals. It learns pretty damn fast: ~15k steps: babbling starts turning into words ~50k steps: it reads anything you type (WER under 1%) ~200k steps: the voice stops sounding synthetic On a beefy consumer GPU, that's a week of training. On eight H100s: 10-20 hours. A TTS training run will cost you less than $200 if you rent your hardware, and an order of magnitude less if you just pay for power. Some things we'd love to see people try: - Train it in your own language (a few hundred hours of speech gets you surprisingly far). - Add new features to Pocket TTS (Emotion tags? Make it sing?). - Beat us at our own game: make it faster and smaller. Show us what you build! We'll highlight the best models and new languages for the whole community to enjoy. Pocket TTS has already found many use cases, from reading for people with visual impairments to making NPCs in video games talk, and we're sure there's much more to do with it! Here's an example of a Czech Pocket TTS. Try just asking your favorite agent to find data and apply the method, and you can have your own. Get started:

If you're looking for a weekend project, how about training your own text-to-speech model from scratch on your own GPU, and then running it on any device's CPU? We just open-sourced the entire Pocket TTS training stack: data pipeline, recipes, and evals. It learns pretty damn fast: ~15k steps: babbling starts turning into words ~50k steps: it reads anything you type (WER under 1%) ~200k steps: the voice stops sounding synthetic On a beefy consumer GPU, that's a week of training. On eight H100s: 10-20 hours. A TTS training run will cost you less than $200 if you rent your hardware, and an order of magnitude less if you just pay for power. Some things we'd love to see people try: - Train it in your own language (a few hundred hours of speech gets you surprisingly far). - Add new features to Pocket TTS (Emotion tags? Make it sing?). - Beat us at our own game: make it faster and smaller. Show us what you build! We'll highlight the best models and new languages for the whole community to enjoy. Pocket TTS has already found many use cases, from reading for people with visual impairments to making NPCs in video games talk, and we're sure there's much more to do with it! Here's an example of a Czech Pocket TTS. Try just asking your favorite agent to find data and apply the method, and you can have your own. Get started:

kyutai

104,778 次观看 • 14 天前

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

FASHN AI

19,211 次观看 • 7 个月前

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

413,003 次观看 • 11 个月前