Speech-to-text workload plugin for mate-bench
Project description
mate-workload-stt
Speech-to-text workload plugin for mate-bench.
Benchmarks STT transcription speed and accuracy using LibriSpeech test-clean audio clips with faster-whisper.
Metrics
| Metric | Description |
|---|---|
rtf |
Real-Time Factor — processing_time / audio_duration (lower is better) |
wer |
Word Error Rate — edit distance / total reference words (lower is better) |
total_audio_seconds |
Total audio processed per run |
Profiles
| Profile | Clips | Audio | Model |
|---|---|---|---|
quick |
5 | ~50 s | whisper-large-v3 |
standard |
20 | ~200 s | whisper-large-v3 |
Usage
mate-bench run stt --profile quick
mate-bench run stt --profile standard
Test data
LibriSpeech test-clean (Panayotov et al., 2015). Licensed CC BY 4.0.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mate_workload_stt-0.1.0.tar.gz.
File metadata
- Download URL: mate_workload_stt-0.1.0.tar.gz
- Upload date:
- Size: 5.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.3 {"installer":{"name":"uv","version":"0.10.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b479b0ef638b4ad95531402601ce51fed5607cf09d4eb3138fe2272f7095feb3
|
|
| MD5 |
0f43f2042a40708a346ca3a045e6bf39
|
|
| BLAKE2b-256 |
f8d9b334d30ba99e2d5d3a5ed7e00350521f35897dcf00c7db6eea8f5f439a69
|
File details
Details for the file mate_workload_stt-0.1.0-py3-none-any.whl.
File metadata
- Download URL: mate_workload_stt-0.1.0-py3-none-any.whl
- Upload date:
- Size: 6.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.3 {"installer":{"name":"uv","version":"0.10.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
91eea7a8303a55c6b90aea62501f59fe941936b66d797ffc385e983e074d8f1c
|
|
| MD5 |
1cad0686d1f58bfd15d58d112a60c2e7
|
|
| BLAKE2b-256 |
cef58e2edd5b75cde419828e2e8e5ec7c31a31e6a2ccefb664741a7725b470f4
|