Hey I’m using the HuBert Model to transcribe a WAV file (speech to text - facebook/hubert-large-ls960-ft · Hugging Face). Is there a way to also get the timestamps for every word?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| [Question] Wav2vec2 word times | 2 | 2765 | June 24, 2021 | |
| A hypothetical question on multi-headed wav2vec2 / hubert models | 0 | 341 | December 15, 2021 | |
| Speech to text model with tensorflow? | 1 | 486 | November 4, 2021 | |
| How to get timestamps for each word in a transcription | 2 | 1992 | September 5, 2023 | |
| Live Transcription/ASR | 0 | 1387 | September 18, 2022 |