| Name | spy-der JSON |
| Version |
0.4.1
JSON |
| download |
| home_page | https://github.com/desh2608/spyder |
| Summary | A simple Python package for fast DER computation |
| upload_time | 2023-06-29 20:02:03 |
| maintainer | |
| docs_url | None |
| author | Desh Raj |
| requires_python | |
| license | |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<h1 align="center">SPYDER</h1>
A simple Python package for fast DER computation.
## Installation
```shell
pip install spy-der
```
To install version with latest features directly from Github:
```shell
pip install git+https://github.com/desh2608/spyder.git@main
```
For development, clone this repository and run:
```shell
pip install --editable .
```
## Usage
### Compute DER for a single pair of reference and hypothesis
```python
import spyder
# reference (ground truth)
ref = [("A", 0.0, 2.0), # (speaker, start, end)
("B", 1.5, 3.5),
("A", 4.0, 5.1)]
# hypothesis (diarization result from your algorithm)
hyp = [("1", 0.0, 0.8),
("2", 0.6, 2.3),
("3", 2.1, 3.9),
("1", 3.8, 5.2)]
# compute DER on full recording
print(spyder.DER(ref, hyp))
# DERMetrics(duration=5.10,miss=9.80%,falarm=21.57%,conf=25.49%,der=56.86%)
# compute DER on single-speaker regions only
print(spyder.DER(ref, hyp, regions="single"))
# DERMetrics(duration=4.10,miss=0.00%,falarm=26.83%,conf=19.51%,der=46.34%)
# compute DER using UEM segments
uem = [(0.5, 5.0)]
print(spyder.DER(ref, hyp, uem=uem))
# DERMetrics(duration=4.50,miss=11.11%,falarm=22.22%,conf=26.67%,der=60.00%)
# compute DER using collar
print(spyder.DER(ref, hyp, collar=0.2))
# DERMetrics(duration=3.10,miss=3.23%,falarm=12.90%,conf=19.35%,der=35.48%)
# get speaker mapping between reference and hypothesis
metrics = spyder.DER(ref, hyp)
print(f"Reference speaker map: {metrics.ref_map}")
print(f"Hypothesis speaker map: {metrics.hyp_map}")
# Reference speaker map: {'A': '0', 'B': '1'}
# Hypothesis speaker map: {'1': '0', '2': '2', '3': '1'}
```
### Compute DER for multiple pairs of reference and hypothesis
```python
import spyder
# for multiple pairs, reference and hypothesis should be lists or dicts
# if lists, ref and hyp must have same length
# reference (ground truth)
ref = {"uttr0":[("A", 0.0, 2.0), # (speaker, start, end)
("B", 1.5, 3.5),
("A", 4.0, 5.1)],
"uttr2":[("A", 0.0, 4.3), # (speaker, start, end)
("C", 6.0, 8.1),
("B", 2.0, 8.5)]}
# hypothesis (diarization result from your algorithm)
hyp = {"uttr0":[("1", 0.0, 0.8),
("2", 0.6, 2.3),
("3", 2.1, 3.9),
("1", 3.8, 5.2)],
"uttr2":[("1", 0.0, 4.5),
("2", 2.5, 8.7)]}
metrics = spyder.DER(ref, hyp)
print(metrics)
# {'Overall': DERMetrics(duration=18.00,miss=17.22%,falarm=8.33%,conf=7.22%,der=32.78%)}
metrics2 = spyder.DER(ref, hyp, per_file=True, verbose=True) # verbose=True to prints per-file results
```
Output:
```
Evaluated 2 recordings on `all` regions. Results:
╒═════════════╤════════════════╤═════════╤════════════╤═════════╤════════╕
│ Recording │ Duration (s) │ Miss. │ F.Alarm. │ Conf. │ DER │
╞═════════════╪════════════════╪═════════╪════════════╪═════════╪════════╡
│ uttr0 │ 5.10 │ 9.80% │ 21.57% │ 25.49% │ 56.86% │
├─────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ uttr2 │ 12.90 │ 20.16% │ 3.10% │ 0.00% │ 23.26% │
├─────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ Overall │ 18.00 │ 17.22% │ 8.33% │ 7.22% │ 32.78% │
╘═════════════╧════════════════╧═════════╧════════════╧═════════╧════════╛
```
Additionally, you can provide UEM and collar parameters similar to single pair case.
### Compute per-file and overall DERs between reference and hypothesis RTTMs using command line tool
Alternatively, __spyder__ can also be invoked from the command line to compute the per-file
and average DERs between reference and hypothesis RTTMs.
```shell
Usage: spyder [OPTIONS] REF_RTTM HYP_RTTM
Options:
-u, --uem PATH UEM file (format: <recording_id> <channel>
<start> <end>)
-p, --per-file If this flag is set, print per file results.
[default: False]
-s, --skip-missing Skip recordings which are missing in
hypothesis (i.e., not counted in missed
speech). [default: False]
-r, --regions [all|single|overlap|nonoverlap]
Only evaluate on the selected region type.
Default is all. - all: all regions. -
single: only single-speaker regions (ignore
silence and multiple speaker). - overlap:
only regions with multiple speakers in the
reference. - nonoverlap: only regions
without multiple speakers in the reference.
[default: all]
-c, --collar FLOAT RANGE Collar size. [default: 0.0]
-m, --print-speaker-map Print speaker mapping for reference and
hypothesis speakers. [default: False]
--help Show this message and exit.
```
Examples:
```shell
> spyder ref_rttm hyp_rttm
Evaluated 16 recordings on `all` regions. Results:
╒═════════════╤════════════════╤═════════╤════════════╤═════════╤════════╕
│ Recording │ Duration (s) │ Miss. │ F.Alarm. │ Conf. │ DER │
╞═════════════╪════════════════╪═════════╪════════════╪═════════╪════════╡
│ Overall │ 33952.95 │ 11.48% │ 2.27% │ 9.81% │ 23.56% │
╘═════════════╧════════════════╧═════════╧════════════╧═════════╧════════╛
> spyder ref_rttm hyp_rttm -r single -p -c 0.25
Evaluated 16 recordings on `single` regions. Results:
╒═════════════════════╤════════════════╤═════════╤════════════╤═════════╤════════╕
│ Recording │ Duration (s) │ Miss. │ F.Alarm. │ Conf. │ DER │
╞═════════════════════╪════════════════╪═════════╪════════════╪═════════╪════════╡
│ EN2002a.Mix-Headset │ 1032.05 │ 0.00% │ 2.98% │ 4.97% │ 7.94% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ EN2002b.Mix-Headset │ 853.56 │ 0.00% │ 3.40% │ 5.39% │ 8.80% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ EN2002c.Mix-Headset │ 1641.68 │ 0.00% │ 1.42% │ 1.05% │ 2.47% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ EN2002d.Mix-Headset │ 1006.27 │ 0.00% │ 3.12% │ 7.14% │ 10.26% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ ES2004a.Mix-Headset │ 539.48 │ 0.00% │ 1.62% │ 5.12% │ 6.74% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ ES2004b.Mix-Headset │ 1582.05 │ 0.00% │ 0.82% │ 1.39% │ 2.21% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ ES2004c.Mix-Headset │ 1526.84 │ 0.00% │ 0.45% │ 1.27% │ 1.72% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ ES2004d.Mix-Headset │ 1172.72 │ 0.00% │ 1.77% │ 9.60% │ 11.37% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ IS1009a.Mix-Headset │ 425.51 │ 0.00% │ 3.94% │ 4.60% │ 8.54% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ IS1009b.Mix-Headset │ 1412.03 │ 0.00% │ 1.23% │ 0.85% │ 2.08% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ IS1009c.Mix-Headset │ 1283.21 │ 0.00% │ 2.74% │ 1.00% │ 3.75% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ IS1009d.Mix-Headset │ 1164.49 │ 0.00% │ 2.27% │ 3.37% │ 5.64% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ TS3003a.Mix-Headset │ 804.27 │ 0.00% │ 0.00% │ 11.28% │ 11.28% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ TS3003b.Mix-Headset │ 1509.49 │ 0.00% │ 0.36% │ 0.75% │ 1.11% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ TS3003c.Mix-Headset │ 1566.84 │ 0.00% │ 1.76% │ 1.74% │ 3.50% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ TS3003d.Mix-Headset │ 1357.45 │ 0.00% │ 2.42% │ 2.93% │ 5.35% │
├─────────────────────┼────────────────┼─────────┼────────────┼─────────┼────────┤
│ Overall │ 18877.94 │ 0.00% │ 1.72% │ 3.29% │ 5.01% │
╘═════════════════════╧════════════════╧═════════╧════════════╧═════════╧════════╛
```
## Why spyder?
* __Fast:__ Implemented in pure C++, and faster than the alternatives (md-eval.pl,
dscore, pyannote.metrics). See this [benchmark](https://desh2608.github.io/2021-03-05-spyder/)
for comparisons with other tools.
* __Stand-alone:__ It has no dependency on any other library. We have our own
implementation of the Hungarian algorithm, for example, instead of using `scipy`.
* __Easy-to-use:__ No need to write the reference and hypothesis turns to files and
read md-eval output with complex regex patterns.
* __Overlap:__ Spyder supports overlapping speech in reference and hypothesis. In addition,
you can compute metrics on just the single-speaker or overlap regions by passing the
keyword argument `regions="single"` or `regions="overlap"`, respectively.
## Contributing
Contributions for core improvements or new recipes are welcome. Please run the following
before creating a pull request.
```bash
pre-commit install
pre-commit run # Running linter checks
```
## Bugs/issues
Please raise an issue in the [issue tracker](https://github.com/desh2608/spyder/issues).
Raw data
{
"_id": null,
"home_page": "https://github.com/desh2608/spyder",
"name": "spy-der",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "",
"author": "Desh Raj",
"author_email": "r.desh26@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/a0/77/26f8cd7a6e80a7766c1bfc83436e8571d988ce0e619e83e09a75bd334e31/spy-der-0.4.1.tar.gz",
"platform": null,
"description": "<h1 align=\"center\">SPYDER</h1>\n\nA simple Python package for fast DER computation.\n\n## Installation\n\n```shell\npip install spy-der\n```\n\nTo install version with latest features directly from Github:\n\n```shell\npip install git+https://github.com/desh2608/spyder.git@main\n```\n\nFor development, clone this repository and run:\n\n```shell\npip install --editable .\n```\n\n## Usage\n### Compute DER for a single pair of reference and hypothesis\n\n```python\nimport spyder\n\n# reference (ground truth)\nref = [(\"A\", 0.0, 2.0), # (speaker, start, end)\n (\"B\", 1.5, 3.5),\n (\"A\", 4.0, 5.1)]\n\n# hypothesis (diarization result from your algorithm)\nhyp = [(\"1\", 0.0, 0.8),\n (\"2\", 0.6, 2.3),\n (\"3\", 2.1, 3.9),\n (\"1\", 3.8, 5.2)]\n\n# compute DER on full recording\nprint(spyder.DER(ref, hyp))\n# DERMetrics(duration=5.10,miss=9.80%,falarm=21.57%,conf=25.49%,der=56.86%)\n\n# compute DER on single-speaker regions only\nprint(spyder.DER(ref, hyp, regions=\"single\"))\n# DERMetrics(duration=4.10,miss=0.00%,falarm=26.83%,conf=19.51%,der=46.34%)\n\n# compute DER using UEM segments\nuem = [(0.5, 5.0)]\nprint(spyder.DER(ref, hyp, uem=uem))\n# DERMetrics(duration=4.50,miss=11.11%,falarm=22.22%,conf=26.67%,der=60.00%)\n\n# compute DER using collar\nprint(spyder.DER(ref, hyp, collar=0.2))\n# DERMetrics(duration=3.10,miss=3.23%,falarm=12.90%,conf=19.35%,der=35.48%)\n\n# get speaker mapping between reference and hypothesis\nmetrics = spyder.DER(ref, hyp)\nprint(f\"Reference speaker map: {metrics.ref_map}\")\nprint(f\"Hypothesis speaker map: {metrics.hyp_map}\")\n# Reference speaker map: {'A': '0', 'B': '1'}\n# Hypothesis speaker map: {'1': '0', '2': '2', '3': '1'}\n```\n\n### Compute DER for multiple pairs of reference and hypothesis\n\n```python\nimport spyder\n\n# for multiple pairs, reference and hypothesis should be lists or dicts\n# if lists, ref and hyp must have same length\n\n# reference (ground truth)\nref = {\"uttr0\":[(\"A\", 0.0, 2.0), # (speaker, start, end)\n (\"B\", 1.5, 3.5),\n (\"A\", 4.0, 5.1)],\n \"uttr2\":[(\"A\", 0.0, 4.3), # (speaker, start, end)\n (\"C\", 6.0, 8.1),\n (\"B\", 2.0, 8.5)]}\n\n# hypothesis (diarization result from your algorithm)\nhyp = {\"uttr0\":[(\"1\", 0.0, 0.8),\n (\"2\", 0.6, 2.3),\n (\"3\", 2.1, 3.9),\n (\"1\", 3.8, 5.2)],\n \"uttr2\":[(\"1\", 0.0, 4.5),\n (\"2\", 2.5, 8.7)]}\n\nmetrics = spyder.DER(ref, hyp)\nprint(metrics)\n# {'Overall': DERMetrics(duration=18.00,miss=17.22%,falarm=8.33%,conf=7.22%,der=32.78%)}\n\nmetrics2 = spyder.DER(ref, hyp, per_file=True, verbose=True) # verbose=True to prints per-file results\n```\nOutput:\n```\nEvaluated 2 recordings on `all` regions. Results:\n\u2552\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2555\n\u2502 Recording \u2502 Duration (s) \u2502 Miss. \u2502 F.Alarm. \u2502 Conf. \u2502 DER \u2502\n\u255e\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2561\n\u2502 uttr0 \u2502 5.10 \u2502 9.80% \u2502 21.57% \u2502 25.49% \u2502 56.86% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 uttr2 \u2502 12.90 \u2502 20.16% \u2502 3.10% \u2502 0.00% \u2502 23.26% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 Overall \u2502 18.00 \u2502 17.22% \u2502 8.33% \u2502 7.22% \u2502 32.78% \u2502\n\u2558\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u255b\n```\n\nAdditionally, you can provide UEM and collar parameters similar to single pair case.\n\n### Compute per-file and overall DERs between reference and hypothesis RTTMs using command line tool\n\nAlternatively, __spyder__ can also be invoked from the command line to compute the per-file\nand average DERs between reference and hypothesis RTTMs.\n\n```shell\nUsage: spyder [OPTIONS] REF_RTTM HYP_RTTM\n\nOptions:\n -u, --uem PATH UEM file (format: <recording_id> <channel>\n <start> <end>)\n\n -p, --per-file If this flag is set, print per file results.\n [default: False]\n\n -s, --skip-missing Skip recordings which are missing in\n hypothesis (i.e., not counted in missed\n speech). [default: False]\n\n -r, --regions [all|single|overlap|nonoverlap]\n Only evaluate on the selected region type.\n Default is all. - all: all regions. -\n single: only single-speaker regions (ignore\n silence and multiple speaker). - overlap:\n only regions with multiple speakers in the\n reference. - nonoverlap: only regions\n without multiple speakers in the reference.\n [default: all]\n\n -c, --collar FLOAT RANGE Collar size. [default: 0.0]\n -m, --print-speaker-map Print speaker mapping for reference and\n hypothesis speakers. [default: False]\n\n --help Show this message and exit.\n```\n\nExamples:\n\n```shell\n> spyder ref_rttm hyp_rttm\nEvaluated 16 recordings on `all` regions. Results:\n\u2552\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2555\n\u2502 Recording \u2502 Duration (s) \u2502 Miss. \u2502 F.Alarm. \u2502 Conf. \u2502 DER \u2502\n\u255e\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2561\n\u2502 Overall \u2502 33952.95 \u2502 11.48% \u2502 2.27% \u2502 9.81% \u2502 23.56% \u2502\n\u2558\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u255b\n\n> spyder ref_rttm hyp_rttm -r single -p -c 0.25\nEvaluated 16 recordings on `single` regions. Results:\n\u2552\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2564\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2555\n\u2502 Recording \u2502 Duration (s) \u2502 Miss. \u2502 F.Alarm. \u2502 Conf. \u2502 DER \u2502\n\u255e\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u256a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2561\n\u2502 EN2002a.Mix-Headset \u2502 1032.05 \u2502 0.00% \u2502 2.98% \u2502 4.97% \u2502 7.94% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 EN2002b.Mix-Headset \u2502 853.56 \u2502 0.00% \u2502 3.40% \u2502 5.39% \u2502 8.80% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 EN2002c.Mix-Headset \u2502 1641.68 \u2502 0.00% \u2502 1.42% \u2502 1.05% \u2502 2.47% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 EN2002d.Mix-Headset \u2502 1006.27 \u2502 0.00% \u2502 3.12% \u2502 7.14% \u2502 10.26% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 ES2004a.Mix-Headset \u2502 539.48 \u2502 0.00% \u2502 1.62% \u2502 5.12% \u2502 6.74% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 ES2004b.Mix-Headset \u2502 1582.05 \u2502 0.00% \u2502 0.82% \u2502 1.39% \u2502 2.21% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 ES2004c.Mix-Headset \u2502 1526.84 \u2502 0.00% \u2502 0.45% \u2502 1.27% \u2502 1.72% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 ES2004d.Mix-Headset \u2502 1172.72 \u2502 0.00% \u2502 1.77% \u2502 9.60% \u2502 11.37% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 IS1009a.Mix-Headset \u2502 425.51 \u2502 0.00% \u2502 3.94% \u2502 4.60% \u2502 8.54% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 IS1009b.Mix-Headset \u2502 1412.03 \u2502 0.00% \u2502 1.23% \u2502 0.85% \u2502 2.08% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 IS1009c.Mix-Headset \u2502 1283.21 \u2502 0.00% \u2502 2.74% \u2502 1.00% \u2502 3.75% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 IS1009d.Mix-Headset \u2502 1164.49 \u2502 0.00% \u2502 2.27% \u2502 3.37% \u2502 5.64% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 TS3003a.Mix-Headset \u2502 804.27 \u2502 0.00% \u2502 0.00% \u2502 11.28% \u2502 11.28% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 TS3003b.Mix-Headset \u2502 1509.49 \u2502 0.00% \u2502 0.36% \u2502 0.75% \u2502 1.11% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 TS3003c.Mix-Headset \u2502 1566.84 \u2502 0.00% \u2502 1.76% \u2502 1.74% \u2502 3.50% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 TS3003d.Mix-Headset \u2502 1357.45 \u2502 0.00% \u2502 2.42% \u2502 2.93% \u2502 5.35% \u2502\n\u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2524\n\u2502 Overall \u2502 18877.94 \u2502 0.00% \u2502 1.72% \u2502 3.29% \u2502 5.01% \u2502\n\u2558\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2567\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u255b\n```\n\n## Why spyder?\n\n* __Fast:__ Implemented in pure C++, and faster than the alternatives (md-eval.pl,\ndscore, pyannote.metrics). See this [benchmark](https://desh2608.github.io/2021-03-05-spyder/)\nfor comparisons with other tools.\n* __Stand-alone:__ It has no dependency on any other library. We have our own\nimplementation of the Hungarian algorithm, for example, instead of using `scipy`.\n* __Easy-to-use:__ No need to write the reference and hypothesis turns to files and\nread md-eval output with complex regex patterns.\n* __Overlap:__ Spyder supports overlapping speech in reference and hypothesis. In addition,\nyou can compute metrics on just the single-speaker or overlap regions by passing the\nkeyword argument `regions=\"single\"` or `regions=\"overlap\"`, respectively.\n\n\n## Contributing\n\nContributions for core improvements or new recipes are welcome. Please run the following\nbefore creating a pull request.\n\n```bash\npre-commit install\npre-commit run # Running linter checks\n```\n\n\n## Bugs/issues\n\nPlease raise an issue in the [issue tracker](https://github.com/desh2608/spyder/issues).\n",
"bugtrack_url": null,
"license": "",
"summary": "A simple Python package for fast DER computation",
"version": "0.4.1",
"project_urls": {
"Homepage": "https://github.com/desh2608/spyder"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "cc1a8ba1d8227a6a22b0d509288fa8e3714c20c3870189f79cd124b9e08e5cef",
"md5": "7619fc9af2b9ba354248f0f0d17ef2ec",
"sha256": "a132c2aeebc91f476cf9bcc7f76daec978387b9098fc62979df900a0d3c70b3f"
},
"downloads": -1,
"filename": "spy_der-0.4.1-cp38-cp38-macosx_10_14_x86_64.whl",
"has_sig": false,
"md5_digest": "7619fc9af2b9ba354248f0f0d17ef2ec",
"packagetype": "bdist_wheel",
"python_version": "cp38",
"requires_python": null,
"size": 118815,
"upload_time": "2023-06-29T20:02:01",
"upload_time_iso_8601": "2023-06-29T20:02:01.559209Z",
"url": "https://files.pythonhosted.org/packages/cc/1a/8ba1d8227a6a22b0d509288fa8e3714c20c3870189f79cd124b9e08e5cef/spy_der-0.4.1-cp38-cp38-macosx_10_14_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "a07726f8cd7a6e80a7766c1bfc83436e8571d988ce0e619e83e09a75bd334e31",
"md5": "08e44e60559a8eb0cbb5225cca76beac",
"sha256": "c89fcd9a3ffcd95c51e32a6ec4363201460440d9e263987a980d464dcce91ec0"
},
"downloads": -1,
"filename": "spy-der-0.4.1.tar.gz",
"has_sig": false,
"md5_digest": "08e44e60559a8eb0cbb5225cca76beac",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 170656,
"upload_time": "2023-06-29T20:02:03",
"upload_time_iso_8601": "2023-06-29T20:02:03.316607Z",
"url": "https://files.pythonhosted.org/packages/a0/77/26f8cd7a6e80a7766c1bfc83436e8571d988ce0e619e83e09a75bd334e31/spy-der-0.4.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-06-29 20:02:03",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "desh2608",
"github_project": "spyder",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "spy-der"
}
