Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

espnet
/

multi-talker-whisper-small-ami

Automatic Speech Recognition

serialized-output-training

Model card Files Files and versions

Instructions to use espnet/multi-talker-whisper-small-ami with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use espnet/multi-talker-whisper-small-ami with ESPnet:

from espnet2.bin.asr_inference import Speech2Text

model = Speech2Text.from_pretrained(
  "espnet/multi-talker-whisper-small-ami"
)

speech, rate = soundfile.read("speech.wav")
text, *_ = model(speech)[0]

Notebooks
Google Colab
Kaggle

multi-talker-whisper-small-ami

968 MB

Ctrl+K

Ctrl+K

1 contributor

History: 8 commits

cyhuang-tw's picture

Add preprocessor_conf.speaker_change_symbol

7eb8434 verified about 1 month ago

.gitattributes

135 Bytes
Track token_list.txt as LFS about 1 month ago
README.md

1.64 kB
Update cpWER table to use whisper.normalizers.EnglishTextNormalizer about 1 month ago
config.yaml

552 kB
Add preprocessor_conf.speaker_change_symbol about 1 month ago
model.pth
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "collections.OrderedDict"
What is a pickle import?
967 MB
xet

Add model.pth about 1 month ago
token_list.txt

376 kB
xet

Add token_list.txt about 1 month ago