mirror of
https://github.com/snakers4/silero-vad.git
synced 2026-02-04 09:29:22 +08:00
fx
This commit is contained in:
18
README.md
18
README.md
@@ -94,7 +94,7 @@ The models are small enough to be included directly into this repository. Newer
|
||||
| `'silero_vad_mini_8k'` | 100K | VAD | Yes | `ru`, `en`, `de`, `es` (*) | :heavy_check_mark: | :heavy_check_mark: | [](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb) |
|
||||
| `'silero_number_detector'` | 1.1M | Number Detector | No | `ru`, `en`, `de`, `es` | :heavy_check_mark: | :heavy_check_mark: | [](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb) |
|
||||
| `'silero_lang_detector'` | 1.1M | Language Classifier | No | `ru`, `en`, `de`, `es` | :heavy_check_mark: | :heavy_check_mark: | [](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb) |
|
||||
| `'silero_lang_detector_116'` | 1.7M | Language Classifier | No | [116 languages](https://github.com/snakers4/silero-vad/files/lang_dict_116.json) | :heavy_check_mark: | :heavy_check_mark: | [](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb) |
|
||||
| `'silero_lang_detector_116'` | 1.7M | Language Classifier | No | [116 languages](https://github.com/snakers4/silero-vad/blob/master/files/lang_dict_116.json) | :heavy_check_mark: | :heavy_check_mark: | [](https://colab.research.google.com/github/snakers4/silero-vad/blob/master/silero-vad.ipynb) |
|
||||
|
||||
(*) Though explicitly trained on these languages, VAD should work on any Germanic, Romance or Slavic Languages out of the box.
|
||||
|
||||
@@ -194,7 +194,8 @@ number_timestamps = get_number_ts(wav, model)
|
||||
pprint(number_timestamps)
|
||||
```
|
||||
|
||||
#### Language Classifier (4 languages)
|
||||
#### Language Classifier
|
||||
##### 4 languages
|
||||
|
||||
[](https://pytorch.org/hub/snakers4_silero-vad_language/)
|
||||
|
||||
@@ -217,7 +218,7 @@ language = get_language(wav, model)
|
||||
pprint(language)
|
||||
```
|
||||
|
||||
#### Language Classifier (116 languages)
|
||||
##### 116 languages
|
||||
|
||||
[](https://pytorch.org/hub/snakers4_silero-vad_language/)
|
||||
|
||||
@@ -325,7 +326,8 @@ number_timestamps = get_number_ts(wav, model, run_function=validate_onnx)
|
||||
pprint(number_timestamps)
|
||||
```
|
||||
|
||||
#### Language Classifier (4 languages)
|
||||
#### Language Classifier
|
||||
##### 4 languages
|
||||
|
||||
```python
|
||||
import torch
|
||||
@@ -357,7 +359,7 @@ language = get_language(wav, model, run_function=validate_onnx)
|
||||
print(language)
|
||||
```
|
||||
|
||||
#### Language Classifier (116 languages)
|
||||
##### 116 languages
|
||||
|
||||
```python
|
||||
import torch
|
||||
@@ -531,10 +533,10 @@ Please see [Quality Metrics](#quality-metrics)
|
||||
- More languages TBD
|
||||
- Arbitrary audio length can be used, although network was trained using audio shorter than 15 seconds
|
||||
|
||||
### How Language Classifier 116
|
||||
### How Language Classifier 116 Works
|
||||
|
||||
- **83%** validation accuracy among 116 languages, **87%** validation accuracy among [77 language groups](https://github.com/snakers4/silero-vad/files/lang_group_dict_116.json)
|
||||
- Language classifier 116 was trained using audio samples in [116 languages](https://github.com/snakers4/silero-vad/files/lang_dict_116.json)
|
||||
- **83%** validation accuracy among 116 languages, **87%** validation accuracy among [77 language groups](https://github.com/snakers4/silero-vad/blob/master/files/lang_group_dict_116.json)
|
||||
- Language classifier 116 was trained using audio samples in [116 languages](https://github.com/snakers4/silero-vad/blob/master/files/lang_dict_116.json)
|
||||
- Arbitrary audio length can be used, although network was trained using audio shorter than 20 seconds
|
||||
|
||||
## Contact
|
||||
|
||||
@@ -6,6 +6,7 @@ from utils_vad import (init_jit_model,
|
||||
get_speech_ts_adaptive,
|
||||
get_number_ts,
|
||||
get_language,
|
||||
get_language_and_group,
|
||||
save_audio,
|
||||
read_audio,
|
||||
state_generator,
|
||||
|
||||
Reference in New Issue
Block a user