mirror of
https://github.com/snakers4/silero-vad.git
synced 2026-02-05 18:09:22 +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_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_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'` | 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.
|
(*) 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)
|
pprint(number_timestamps)
|
||||||
```
|
```
|
||||||
|
|
||||||
#### Language Classifier (4 languages)
|
#### Language Classifier
|
||||||
|
##### 4 languages
|
||||||
|
|
||||||
[](https://pytorch.org/hub/snakers4_silero-vad_language/)
|
[](https://pytorch.org/hub/snakers4_silero-vad_language/)
|
||||||
|
|
||||||
@@ -217,7 +218,7 @@ language = get_language(wav, model)
|
|||||||
pprint(language)
|
pprint(language)
|
||||||
```
|
```
|
||||||
|
|
||||||
#### Language Classifier (116 languages)
|
##### 116 languages
|
||||||
|
|
||||||
[](https://pytorch.org/hub/snakers4_silero-vad_language/)
|
[](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)
|
pprint(number_timestamps)
|
||||||
```
|
```
|
||||||
|
|
||||||
#### Language Classifier (4 languages)
|
#### Language Classifier
|
||||||
|
##### 4 languages
|
||||||
|
|
||||||
```python
|
```python
|
||||||
import torch
|
import torch
|
||||||
@@ -357,7 +359,7 @@ language = get_language(wav, model, run_function=validate_onnx)
|
|||||||
print(language)
|
print(language)
|
||||||
```
|
```
|
||||||
|
|
||||||
#### Language Classifier (116 languages)
|
##### 116 languages
|
||||||
|
|
||||||
```python
|
```python
|
||||||
import torch
|
import torch
|
||||||
@@ -531,10 +533,10 @@ Please see [Quality Metrics](#quality-metrics)
|
|||||||
- More languages TBD
|
- More languages TBD
|
||||||
- Arbitrary audio length can be used, although network was trained using audio shorter than 15 seconds
|
- 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)
|
- **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/files/lang_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
|
- Arbitrary audio length can be used, although network was trained using audio shorter than 20 seconds
|
||||||
|
|
||||||
## Contact
|
## Contact
|
||||||
|
|||||||
@@ -6,6 +6,7 @@ from utils_vad import (init_jit_model,
|
|||||||
get_speech_ts_adaptive,
|
get_speech_ts_adaptive,
|
||||||
get_number_ts,
|
get_number_ts,
|
||||||
get_language,
|
get_language,
|
||||||
|
get_language_and_group,
|
||||||
save_audio,
|
save_audio,
|
||||||
read_audio,
|
read_audio,
|
||||||
state_generator,
|
state_generator,
|
||||||
|
|||||||
Reference in New Issue
Block a user