lihongjie commited on
Commit
39ad93d
·
1 Parent(s): 41b3743
Files changed (1) hide show
  1. README.md +37 -8
README.md CHANGED
@@ -42,24 +42,28 @@ For those who are interested in model conversion, you can try to export axmodel
42
 
43
  Download all files from this repository to the device
44
 
45
- ### 1. Text to Speech (Voice Cloning)
46
 
47
- #### (1) Copy this project to AX650 Board
48
 
49
- #### (2). Prepare Dependencies
50
 
51
  **Running HTTP Tokenizer Server** and **Processing Prompt Speech** require these Python packages. If you run these two step on a PC, install them on the PC.
52
  ```
53
  pip3 install -r scripts/requirements.txt
54
  ```
55
 
56
- #### 2. Start HTTP Tokenizer Server
57
  ```
58
  cd scripts
59
  python cosyvoice2_tokenizer.py --host {your host} --port {your port}
60
  ```
61
 
62
- #### 3. Run on AX650 Board
 
 
 
 
63
  1) Moidfy the HTTP host in `run_ax650.sh`.
64
 
65
  2) Run `run_ax650.sh`
@@ -127,17 +131,42 @@ Output Speech:
127
  [output.wav](asset/output.wav)
128
 
129
 
130
- #### Optional. Process Prompt Speech
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
131
  If you want to replicate a specific sound, do this step.
132
  You can use audio in asset/ .
133
 
134
- ##### (1). Downlaod wetext
135
  ```
136
  pip3 install modelscope
137
  modelscope download --model pengzhendong/wetext --local_dir pengzhendong/wetext
138
  ```
139
 
140
- ##### (2). Process Prompt Speech
141
  Example:
142
  ```
143
  python3 scripts/process_prompt.py --prompt_text asset/zh_man1.txt --prompt_speech asset/zh_man1.wav --output zh_man1
 
42
 
43
  Download all files from this repository to the device
44
 
45
+ ### 1. PrePare
46
 
47
+ #### 1.1 Copy this project to AX650 Board
48
 
49
+ #### 1.2 Prepare Dependencies
50
 
51
  **Running HTTP Tokenizer Server** and **Processing Prompt Speech** require these Python packages. If you run these two step on a PC, install them on the PC.
52
  ```
53
  pip3 install -r scripts/requirements.txt
54
  ```
55
 
56
+ ### 2. Start HTTP Tokenizer Server
57
  ```
58
  cd scripts
59
  python cosyvoice2_tokenizer.py --host {your host} --port {your port}
60
  ```
61
 
62
+
63
+ ### 3. Run on Axera Device
64
+ There are 2 kinds of device, AX650 Board and AXCL aarch64 Board.
65
+
66
+ #### 3.1 Run on AX650 Board
67
  1) Moidfy the HTTP host in `run_ax650.sh`.
68
 
69
  2) Run `run_ax650.sh`
 
131
  [output.wav](asset/output.wav)
132
 
133
 
134
+ #### Or run on AX650 Board with Gradio GUI
135
+ 1) Start server
136
+ ```
137
+ bash run_api_ax650.sh
138
+ ```
139
+ 2) Start Gradio GUI
140
+ ```
141
+ python scripts/gradio_demo.py
142
+ ```
143
+
144
+ #### 3.2 Run on AXCL aarch64 Board
145
+ ```
146
+ bash run_axcl_aarch64.sh
147
+ ```
148
+ #### Or run on AXCL aarch64 Board with Gradio GUI
149
+ 1) Start server
150
+ ```
151
+ bash run_api_axcl_aarch64.sh
152
+ ```
153
+ 2) Start Gradio GUI
154
+ ```
155
+ python scripts/gradio_demo.py
156
+ ```
157
+
158
+
159
+ ### Optional. Process Prompt Speech
160
  If you want to replicate a specific sound, do this step.
161
  You can use audio in asset/ .
162
 
163
+ #### (1). Downlaod wetext
164
  ```
165
  pip3 install modelscope
166
  modelscope download --model pengzhendong/wetext --local_dir pengzhendong/wetext
167
  ```
168
 
169
+ #### (2). Process Prompt Speech
170
  Example:
171
  ```
172
  python3 scripts/process_prompt.py --prompt_text asset/zh_man1.txt --prompt_speech asset/zh_man1.wav --output zh_man1