Downloads · 30 days
0
khassan_KSC_transformer
espnet/khassan_KSC_transformer
khassan_KSC_transformer is a automatic speech recognition model from espnet. Use it when you need speech turned into text. It is set up for espnet. The card lists the license as cc-by-4.0.
- date: Mon May 15 16:32:55 CST 2023 - python version: 3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0] - espnet version: espnet 202304 - pytorch version: pytorch 1.13.1 - Git hash: 3949a7db023d591e91627efb997eda35…
Access
Public
Updated May 16, 2023
Repo size
2.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth1.6 GB · 42%
At a glance
- Task
- Automatic Speech Recognition
- Library
- espnet
- License
- cc-by-4.0
- Access
- Public
- Created
- May 15, 2023
- Updated
- May 16, 2023
- SHA
- 534e72c4
Model card
From the Hugging Face model README
<!-- Generated by scripts/utils/show_asr_result.sh -->
RESULTS
Environments
- date:
Mon May 15 16:32:55 CST 2023 - python version:
3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0] - espnet version:
espnet 202304 - pytorch version:
pytorch 1.13.1 - Git hash:
3949a7db023d591e91627efb997eda353b54005d- Commit date:
Thu May 11 17:54:50 2023 +0800
- Commit date:
exp/asr_train_raw_bpe2000_sp
WER
| dataset | Snt | Wrd | Corr | Sub | Del | Ins | Err | S.Err |
|---|---|---|---|---|---|---|---|---|
| decode_asr_model_valid.acc.ave/test | 3334 | 35884 | 90.6 | 8.6 | 0.8 | 1.1 | 10.5 | 55.1 |
CER
| dataset | Snt | Wrd | Corr | Sub | Del | Ins | Err | S.Err |
|---|---|---|---|---|---|---|---|---|
| decode_asr_model_valid.acc.ave/test | 3334 | 259552 | 97.9 | 1.2 | 0.9 | 0.8 | 2.9 | 55.1 |
TER
| dataset | Snt | Wrd | Corr | Sub | Del | Ins | Err | S.Err |
|---|---|---|---|---|---|---|---|---|
| decode_asr_model_valid.acc.ave/test | 3334 | 71707 | 91.9 | 5.6 | 2.5 | 1.1 | 9.2 | 55.1 |
exp/asr_train_raw_bpe2000_sp/decode_asr_model_valid.acc.ave
WER
| dataset | Snt | Wrd | Corr | Sub | Del | Ins | Err | S.Err |
|---|---|---|---|---|---|---|---|---|
| org/dev | 3283 | 35275 | 89.0 | 10.0 | 1.0 | 1.2 | 12.1 | 59.0 |
CER
| dataset | Snt | Wrd | Corr | Sub | Del | Ins | Err | S.Err |
|---|---|---|---|---|---|---|---|---|
| org/dev | 3283 | 253600 | 97.4 | 1.4 | 1.2 | 1.0 | 3.5 | 59.0 |
TER
| dataset | Snt | Wrd | Corr | Sub | Del | Ins | Err | S.Err |
|---|---|---|---|---|---|---|---|---|
| org/dev | 3283 | 69428 | 90.5 | 6.7 | 2.8 | 1.3 | 10.8 | 59.0 |
- Task
- Automatic Speech Recognition
- Library
- espnet
- License
- cc-by-4.0
- Languages
- kk
- Created
- May 15, 2023
- Updated
- May 16, 2023