kyegomez / USM
Implementation of Google's USM speech model in Pytorch
☆27Updated this week
Alternatives and similar repositories for USM:
Users that are interested in USM are comparing it to the libraries listed below
- Official release of StyleTalk dataset.☆60Updated 6 months ago
- LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models☆23Updated 5 months ago
- Interface Design for Self-Supervised Speech Models, Accepted to Interspeech2024☆15Updated 2 months ago
- Official Code for ParrotTTS☆46Updated 3 months ago
- ☆34Updated 9 months ago
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆60Updated 2 months ago
- Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".☆24Updated 6 months ago
- ☆18Updated 8 months ago
- We introduce the LLAMA1 Test Set, a comprehensive open-domain world knowledge QA dataset for evaluating question-answering systems. We pr…☆16Updated 10 months ago
- ☆25Updated last year
- A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.☆28Updated 3 months ago
- ☆56Updated 2 years ago
- Temporary anonymous version☆22Updated 10 months ago
- （WIP）long form speech generatoins☆29Updated last month
- SLMTokBench for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"☆33Updated last year
- Implementation of CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning☆46Updated last year
- Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark☆25Updated 6 months ago
- Collection of scripts from mHuBERT-147.☆24Updated 2 months ago
- GPT for FACodec☆13Updated 10 months ago
- Official Code for SyllableLM: Learning Coarse Semantic Units for Speech Language Models☆41Updated 3 months ago
- ☆12Updated 10 months ago
- ☆35Updated 4 months ago
- ☆21Updated 5 months ago
- Pushing the Limits of Zero-shot End-to-End Speech Translation☆25Updated last month
- (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.☆47Updated last year
- ConMamba for Automatic Speech Recognition☆54Updated 5 months ago
- ☆26Updated 10 months ago
- Implementation of the model "AudioFlamingo" from the paper: "Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dial…☆40Updated this week
- Official repository for NAST: Noise Aware Speech Tokenization for Speech Language Models (Interspeech 2024) https://arxiv.org/abs/2406.11…☆44Updated 6 months ago
- ☆24Updated last year