Downloads · 30 days
0
icefall-asr-tedlium3-conformer-ctc2
videodanchik/icefall-asr-tedlium3-conformer-ctc2
icefall-asr-tedlium3-conformer-ctc2 is a automatic speech recognition model from videodanchik. Use it when you need speech turned into text. It is set up for k2. The card lists the license as cc-by-nc-nd-3.0.
This is an ASR ctc attention encoder-decoder recipe for the Tedlium3 corpus. The encoder is the re-worked conformer model. Language models are downloaded from https://kaldi-asr.org/models/m5
Access
Public
Updated Dec 19, 2022
Repo size
2.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.8 GB · 74%
At a glance
- Task
- Automatic Speech Recognition
- Library
- k2
- License
- cc-by-nc-nd-3.0
- Access
- Public
- Created
- Dec 11, 2022
- Updated
- Dec 19, 2022
- SHA
- 2e88d7e5
Datasets
Model card
From the Hugging Face model README
Tedlium3
This is an ASR ctc attention encoder-decoder recipe for the Tedlium3 corpus. The encoder is the re-worked conformer model. Language models are downloaded from https://kaldi-asr.org/models/m5
Performance Record
conformer_ctc2
| Decodeing method | dev WER | test WER |
|---|---|---|
| ctc-decoding | 6.45 | 5.96 |
| 1best | 5.92 | 5.51 |
| whole-lattice-rescoring | 5.96 | 5.47 |
| attention-decoder | 5.60 | 5.33 |
See the recipe for details.
- Task
- Automatic Speech Recognition
- Library
- k2
- License
- cc-by-nc-nd-3.0
- Languages
- en
- Created
- Dec 11, 2022
- Updated
- Dec 19, 2022