update

.gitattributes

@@ -110,3 +110,4 @@ token2wav-axmodels/hift_p2_58.axmodel filter=lfs diff=lfs merge=lfs -text
 token2wav-axmodels/rand_noise_1_80_300.txt filter=lfs diff=lfs merge=lfs -text
 token2wav-axmodels/speech_window_2x8x480.txt filter=lfs diff=lfs merge=lfs -text
 token2wav-axmodels/hift_p1_50_first.mnn filter=lfs diff=lfs merge=lfs -text
+main_axcl_aarch64 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -59,11 +59,11 @@ python cosyvoice2_tokenizer.py --host {your host} --port {your port}
 ```
 
 #### 3. Run on AX650 Board  
-1) Moidfy the HTTP host in `run.sh`.  
+1) Moidfy the HTTP host in `run_ax650.sh`.  
 
-2) Run `run.sh`  
+2) Run `run_ax650.sh`  
 ```shell
-root@ax650 ~/Cosyvoice2 # bash run.sh 
+root@ax650 ~/Cosyvoice2 # bash run_ax650.sh 
 rm: cannot remove 'output*.wav': No such file or directory
 [I][                            Init][ 108]: LLM init start
 [I][                            Init][  34]: connect http://10.122.86.184:12345 ok
@@ -174,4 +174,4 @@ prompt_speech_feat.txt
 prompt_text.txt
 ```
 
-When you run run.sh, pass the output path here to the prompt_files parameter of the run.sh script.
+When you run run_ax650.sh, pass the output path here to the prompt_files parameter of the run_ax650.sh script.

main_axcl_aarch64

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c4e2487588e29adc12fdefcddb0dbd18c52b84862736c3960062ecf40baee15
+size 4822152

run_axcl_aarch64.sh

@@ -0,0 +1,23 @@
+LLM_DIR=CosyVoice-BlankEN-Ax650-prefill_512/
+TOKEN2WAV_DIR=token2wav-axmodels/
+
+rm output*.wav
+./main_axcl_aarch64 \
+--template_filename_axmodel "${LLM_DIR}/qwen2_p128_l%d_together.axmodel" \
+--token2wav_axmodel_dir $TOKEN2WAV_DIR \
+--n_timesteps 10 \
+--axmodel_num 24 \
+--bos 0 --eos 0 \
+--filename_tokenizer_model "http://127.0.0.1:12345" \
+--filename_post_axmodel "${LLM_DIR}/qwen2_post.axmodel" \
+--filename_decoder_axmodel "${LLM_DIR}/llm_decoder.axmodel" \
+--filename_tokens_embed "${LLM_DIR}/model.embed_tokens.weight.bfloat16.bin" \
+--filename_llm_embed "${LLM_DIR}/llm.llm_embedding.float16.bin" \
+--filename_speech_embed "${LLM_DIR}/llm.speech_embedding.float16.bin" \
+--continue 0 \
+--devices "0," \
+--prompt_files prompt_files \
+--text "君不见黄河之水天上来，奔流到海不复回。君不见高堂明镜悲白发，朝如青丝暮成雪。"
+
+
+chmod 777 output*.wav