asr-decoder
CTC decoder with hotwords for ASR models. Supports ctc_greedy_search and ctc_prefix_bream_search decoding methods.
Usage
- ctc greedy search
from asr_decoder import CTCDecoder
decoder = CTCDecoder()
# ctc_probs: (sequence_length, vocab_size)
result = decoder.ctc_greedy_search(ctc_probs, is_last=True)
- ctc prefix beam search (with hotwords)
from asr_decoder import CTCDecoder
hotwords = ["停止"]
decoder = CTCDecoder(hotwords, symbol_table, bpemodel)
# ctc_probs: (sequence_length, vocab_size)
result = decoder.ctc_prefix_beam_search(ctc_probs, beam_size=3, is_last=True)
1 maintainer
Metadata
1 maintainer
Release files for asr-decoder 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| asr_decoder-0.1.2-py3-none-any.whl | Python 3 | none | any | Details |
Release files / asr_decoder-0.1.2-py3-none-any.whl
| Download URL | asr_decoder-0.1.2-py3-none-any.whl |
|---|---|
| Size | 13.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1c698df3ba49c23d5f86b4730b7c6d815c681fcb9a47d0c0ac5e243d30e03b0c
|
|
BLAKE2b-256 checksum How to use checksums |
03a0b7a7c0eb20e0efaa04fd784b8bdfacac33c9866bd18e209c498118a4c935
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
