TED-LIUM
Introduced by Rousseau et al. in TED-LIUM: an Automatic Speech Recognition dedicated corpus
The TED-LIUM corpus consists of English-language TED talks. It includes transcriptions of these talks. The audio is sampled at 16kHz. The dataset spans a range of 118 to 452 hours of transcribed speech data.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Tedlium
|
United-MedASR
|
|||
|
TED-LIUM
|
Whisper-LLaMa-7b
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
