Automatic Speech Recognition
ESPnet
multilingual
audio
phone-recognition
grapheme-to-phoneme
phoneme-to-grapheme
Instructions to use espnet/powsm_ctc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/powsm_ctc with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/powsm_ctc" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
add files
Browse files- exp/{train → s2t_stats_raw_bpe40000/train}/feats_stats.npz +0 -0
- exp/s2t_train_conv2d_size768_e9_d9_mel80_raw_bpe40000/config.yaml +0 -0
- exp/{train_conv2d_size768_e9_d9_mel80_raw_bpe40000 → s2t_train_conv2d_size768_e9_d9_mel80_raw_bpe40000}/valid.total_count.ave_5best.till70epoch.pth +0 -0
- meta.yaml +7 -0
exp/{train → s2t_stats_raw_bpe40000/train}/feats_stats.npz
RENAMED
|
File without changes
|
exp/s2t_train_conv2d_size768_e9_d9_mel80_raw_bpe40000/config.yaml
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
exp/{train_conv2d_size768_e9_d9_mel80_raw_bpe40000 → s2t_train_conv2d_size768_e9_d9_mel80_raw_bpe40000}/valid.total_count.ave_5best.till70epoch.pth
RENAMED
|
File without changes
|
meta.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
espnet: '202509' # with unmerged local change; will update to suitable version
|
| 2 |
+
files:
|
| 3 |
+
s2t_model_file: exp/s2t_train_conv2d_size768_e9_d9_mel80_raw_bpe40000/valid.total_count.ave_5best.till70epoch.pth
|
| 4 |
+
python: 3.12.8
|
| 5 |
+
torch: 2.9.1+cu128
|
| 6 |
+
yaml_files:
|
| 7 |
+
s2t_train_config: exp/s2t_train_conv2d_size768_e9_d9_mel80_raw_bpe40000/config.yaml
|