Downloads · 30 days
3.6K
0% of all-time downloads
reazonspeech-nemo-v2
reazon-research/reazonspeech-nemo-v2
reazonspeech-nemo-v2 is a automatic speech recognition model from reazon-research. Use it when you need speech turned into text. It is set up for nemo. The card lists the license as apache-2.0.
reazonspeech-nemo-v2 is an automatic speech recognition model trained on ReazonSpeech v2.0 corpus.
All-time downloads
1.5M
Public
Repo size
2.5 GB
Likes
41
Public
Repo makeup
Click a slice to open those files.
.nemo2.5 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- nemo
- License
- apache-2.0
- Access
- Public
- Created
- Jan 30, 2024
- Updated
- Feb 13, 2024
- SHA
- 33693408
Model card
From the Hugging Face model README
reazonspeech-nemo-v2
reazonspeech-nemo-v2 is an automatic speech recognition model trained
on ReazonSpeech v2.0 corpus.
This model supports inference of long-form Japanese audio clips up to several hours.
Model Architecture
The model features an improved Conformer architecture from Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition.
-
Subword-based RNN-T model. The total parameter count is 619M.
-
Encoder uses Longformer attention with local context size of 256, and has a single global token.
-
Decoder has a vocabulary space of 3000 tokens constructed by SentencePiece unigram tokenizer.
We trained this model for 1 million steps using AdamW optimizer following Noam annealing schedule.
Usage
We recommend to use this model through our reazonspeech library.
from reazonspeech.nemo.asr import load_model, transcribe, audio_from_path
audio = audio_from_path("speech.wav")
model = load_model()
ret = transcribe(model, audio)
print(ret.text)
License
- Task
- Automatic Speech Recognition
- Library
- nemo
- License
- apache-2.0
- Languages
- ja
- Created
- Jan 30, 2024
- Updated
- Feb 13, 2024