mirror of
https://github.com/espressif/esp-sr.git
synced 2025-09-15 15:28:44 +08:00
Merge branch 'wn9/xiaomingtongxue' into 'master'
Wn9/xiaomingtongxue See merge request speech-recognition-framework/esp-sr!142
This commit is contained in:
commit
4f63e6257e
@ -192,6 +192,10 @@ menu "Load Multiple Wake Words"
|
||||
config SR_WN_WN9_XIAOYUTONGXUE_TTS2
|
||||
bool "小宇同学 (wn9_xiaoyutongxue_tts2)"
|
||||
default False
|
||||
|
||||
config SR_WN_WN9_XIAOMINGTONGXUE_TTS2
|
||||
bool "小明同学 (wn9_xiaomingtongxue_tts2)"
|
||||
default False
|
||||
endmenu
|
||||
|
||||
|
||||
|
||||
@ -68,6 +68,7 @@ The following wake words are supported in esp-sr:
|
||||
|璃奈板 | | wn9_linaiban_tts2 |
|
||||
|小酥肉 | | wn9_xiaosurou_tts2 |
|
||||
|小宇同学 | | wn9_xiaoyutongxue_tts2 |
|
||||
|小明同学 | | wn9_xiaomingtongxue_tts2|
|
||||
|
||||
*NOTE:* `_tts` suffix means this WakeNet model is trained by TTS samples. `_tts2` suffix means this WakeNet model is trained by TTS Pipeline V2.
|
||||
|
||||
|
||||
@ -4,6 +4,25 @@ rstCopy
|
||||
|
||||
:link_to_translation:`en:[English]`
|
||||
|
||||
输入数据格式修改
|
||||
---------------------------
|
||||
|
||||
新版本通过 ``input_format`` 参数定义了输入数据中音频通道的排列方式。字符串中的每个字符代表一种通道类型:
|
||||
|
||||
+-----------+---------------------+
|
||||
| 字符 | 描述 |
|
||||
+===========+=====================+
|
||||
| ``M`` | 麦克风通道 |
|
||||
+-----------+---------------------+
|
||||
| ``R`` | 播放参考通道 |
|
||||
+-----------+---------------------+
|
||||
| ``N`` | 未使用或未知通道 |
|
||||
+-----------+---------------------+
|
||||
|
||||
**示例:**
|
||||
``MMNR`` 表示四个通道,依次为:麦克风通道、麦克风通道、未使用通道、播放参考通道。
|
||||
|
||||
|
||||
配置和初始化
|
||||
--------------------------------
|
||||
|
||||
@ -20,26 +39,6 @@ rstCopy
|
||||
|
||||
esp_afe_sr_iface_t *afe_handle = esp_afe_handle_from_config(afe_config);
|
||||
|
||||
输入数据格式修改
|
||||
---------------------------
|
||||
|
||||
新版本通过 ``input_format`` 参数支持更灵活的输入格式。此参数定义了输入数据中音频通道的排列方式。
|
||||
|
||||
因此,您只需要提供正确的 ``input_format``,无需重新排列音频数据。字符串中的每个字符代表一种通道类型:
|
||||
|
||||
+-----------+---------------------+
|
||||
| 字符 | 描述 |
|
||||
+===========+=====================+
|
||||
| ``M`` | 麦克风通道 |
|
||||
+-----------+---------------------+
|
||||
| ``R`` | 播放参考通道 |
|
||||
+-----------+---------------------+
|
||||
| ``N`` | 未使用或未知通道 |
|
||||
+-----------+---------------------+
|
||||
|
||||
**示例:**
|
||||
``MMNR`` 表示四个通道,依次为:麦克风通道、麦克风通道、未使用通道、播放参考通道。
|
||||
|
||||
.. note::
|
||||
|
||||
AFE v2.0 引入了额外的配置选项。详细信息请参阅 :doc:`AFE <../audio_front_end/README>` 和 :doc:`VAD <../vadnet/README>`。
|
||||
@ -0,0 +1 @@
|
||||
wakenet9l_tts2h12_小明同学_3_0.626_0.632
|
||||
BIN
model/wakenet_model/wn9_xiaomingtongxue_tts2/wn9_data
Normal file
BIN
model/wakenet_model/wn9_xiaomingtongxue_tts2/wn9_data
Normal file
Binary file not shown.
BIN
model/wakenet_model/wn9_xiaomingtongxue_tts2/wn9_index
Normal file
BIN
model/wakenet_model/wn9_xiaomingtongxue_tts2/wn9_index
Normal file
Binary file not shown.
Loading…
Reference in New Issue
Block a user