thevoicecompany / gazelle-train
Joint speech-language model - respond directly to audio!
☆29Updated 4 months ago
Related projects: ⓘ
- ☆61Updated last month
- Trying to build an all in one speech-text language model - a bit like GPT-4o☆18Updated 3 months ago
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆34Updated this week
- Speaker Diarization with Transformers☆57Updated 3 months ago
- ☆48Updated last month
- On-device intelligence.☆136Updated last week
- VoiceBox neural network implementation☆88Updated last month
- Audio tokenization, in the fastest way possible!☆43Updated 3 weeks ago
- ☆149Updated last year
- lina-speech : linear attention based text-to-speech☆111Updated 3 months ago
- Promting Whisper for Audio-Visual Speech Recognition, Code-Switched Speech Recognition, and Zero-Shot Speech Translation☆132Updated 8 months ago
- Speech recognition & diarisation solution with text alignment, deployed in AML pipelines☆81Updated 4 months ago
- A synthetic story narration dataset to study small audio LMs.☆28Updated 7 months ago
- An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GP…☆74Updated 2 months ago
- Llama3.1 learns to Listen☆134Updated this week
- Tokun to can tokens☆13Updated this week
- ☆241Updated 3 months ago
- Efficient approach to speaker diarization using voice characteristics extraction☆56Updated 4 months ago
- Google's SoundStorm: Efficient Parallel Audio Generation☆115Updated last year
- Speaker diarization service☆17Updated last week
- Create an LJSpeech structured voice dataset on wave input☆16Updated 2 months ago
- ☆244Updated 6 months ago
- VALL-E 2 reproduction☆72Updated 2 months ago
- Video+code lecture on building nanoGPT from scratch☆64Updated 3 months ago
- Training Models Daily☆17Updated 9 months ago
- 🌼 Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition☆14Updated 6 months ago
- ☆84Updated 5 months ago
- StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion☆72Updated this week
- ☆272Updated 2 weeks ago
- Supervoice diffusion enhance☆24Updated 2 months ago