Hello everyone is anyone worked on enhancing the output of STT using LLM? tell about the best STT that you used I faced problem that the STT is not capturing all the text. could I use the LLM to enhnace the audio quality before feed it to the STT model?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| STT for stroke victims and unrecognisable speech | 7 | 51 | September 9, 2024 | |
| Speech to Speech system | 3 | 47 | January 25, 2025 | |
| Finetuning logs | 0 | 97 | September 22, 2023 | |
| Fine-Tuning a Large Language Models with QLoRA and PEFT(LLMs) | 11 | 713 | July 15, 2023 | |
| LLM Post processing with Streaming | 0 | 165 | January 18, 2024 |