From d80ac2fd2df4e7fb8a28acfa512bb11472b5cc99 Mon Sep 17 00:00:00 2001
From: liugz18 <57401541+liugz18@users.noreply.github.com>
Date: 星期四, 18 七月 2024 21:34:55 +0800
Subject: [PATCH] Rename 'res' in line 514 to avoid with naming conflict with line 365
---
examples/README.md | 40 ++++++++++++++++++++++++++++++++++------
1 files changed, 34 insertions(+), 6 deletions(-)
diff --git a/examples/README.md b/examples/README.md
index 20102cc..fe9a0ed 100644
--- a/examples/README.md
+++ b/examples/README.md
@@ -69,6 +69,34 @@
#### Speech Recognition (Non-streaming)
+##### SenseVoice
+```python
+from funasr import AutoModel
+from funasr.utils.postprocess_utils import rich_transcription_postprocess
+
+model_dir = "iic/SenseVoiceSmall"
+
+model = AutoModel(
+ model=model_dir,
+ vad_model="fsmn-vad",
+ vad_kwargs={"max_single_segment_time": 30000},
+ device="cuda:0",
+)
+
+# en
+res = model.generate(
+ input=f"{model.model_path}/example/en.mp3",
+ cache={},
+ language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
+ use_itn=True,
+ batch_size_s=60,
+ merge_vad=True, #
+ merge_length_s=15,
+)
+text = rich_transcription_postprocess(res[0]["text"])
+print(text)
+```
+##### Paraformer
```python
from funasr import AutoModel
# paraformer-zh is a multi-functional asr model
@@ -130,7 +158,7 @@
from funasr import AutoModel
model = AutoModel(model="fsmn-vad")
-wav_file = f"{model.model_path}/example/asr_example.wav"
+wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
@@ -221,7 +249,7 @@
++train_conf.validate_interval=2000 \
++train_conf.save_checkpoint_interval=2000 \
++train_conf.keep_nbest_models=20 \
-++train_conf.avg_nbest_model=5 \
+++train_conf.avg_nbest_model=10 \
++optim_conf.lr=0.0002 \
++output_dir="${output_dir}" &> ${log_file}
```
@@ -248,10 +276,10 @@
export CUDA_VISIBLE_DEVICES="0,1"
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
-torchrun --nnodes 1 --nproc_per_node ${gpu_num} \
+torchrun --nnodes 1 --nproc_per_node ${gpu_num} --master_port 12345 \
../../../funasr/bin/train.py ${train_args}
```
---nnodes represents the total number of participating nodes, while --nproc_per_node indicates the number of processes running on each node.
+--nnodes represents the total number of participating nodes, while --nproc_per_node indicates the number of processes running on each node. --master_port indicates the port is 12345
##### Multi-Machine Multi-GPU Training
@@ -260,7 +288,7 @@
export CUDA_VISIBLE_DEVICES="0,1"
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
-torchrun --nnodes 2 --node_rank 0 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --master_port=12345 \
+torchrun --nnodes 2 --node_rank 0 --nproc_per_node ${gpu_num} --master_addr 192.168.1.1 --master_port 12345 \
../../../funasr/bin/train.py ${train_args}
```
On the worker node (assuming the IP is 192.168.1.2), you need to ensure that the MASTER_ADDR and MASTER_PORT environment variables are set to match those of the master node, and then run the same command:
@@ -269,7 +297,7 @@
export CUDA_VISIBLE_DEVICES="0,1"
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
-torchrun --nnodes 2 --node_rank 1 --nproc_per_node ${gpu_num} --master_addr=192.168.1.1 --master_port=12345 \
+torchrun --nnodes 2 --node_rank 1 --nproc_per_node ${gpu_num} --master_addr 192.168.1.1 --master_port 12345 \
../../../funasr/bin/train.py ${train_args}
```
--
Gitblit v1.9.1