| Commit message (Collapse) | Author | Age | |
|---|---|---|---|
| * | begin work disabling vad | yum | 2023-03-17 |
| | | |||
| * | Use logprobs, fix beam candidate selection | yum | 2023-03-03 |
| | | | | | | | | | | | | | | Incorrect sort condition resulted in worst 5 beams being picked instead of best 5. Use log probabilities for joint probability calculation instead of linear probabilities. Long beams would have probabilities converge exponentially towards zero; now they converge linearly towards -INFINITY. Using both transcripts in Evaluation/setup.ps1, I see a small edit distance regression (~5%) using beam search vs. greedy. | ||
| * | Begin work on evaluation framework | yum | 2023-03-03 |
| Need a way to verify that beam search is actually working better than greedy. | |||
 |
index : TaSTT-Whisper.git | |
| High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model |
| summaryrefslogtreecommitdiffstats |