From bced0c251b390067de435237446065cecbcf2760 Mon Sep 17 00:00:00 2001
From: Yabin Li <wucong.lyb@alibaba-inc.com>
Date: 星期四, 06 四月 2023 14:21:24 +0800
Subject: [PATCH] Merge pull request #290 from veelion/main
---
funasr/runtime/grpc/paraformer_server.cc | 26 +++++++-----
funasr/runtime/grpc/Readme.md | 62 +++++++++++++++++++++++++++++++
2 files changed, 77 insertions(+), 11 deletions(-)
diff --git a/funasr/runtime/grpc/Readme.md b/funasr/runtime/grpc/Readme.md
index 6e3516a..82347be 100644
--- a/funasr/runtime/grpc/Readme.md
+++ b/funasr/runtime/grpc/Readme.md
@@ -53,6 +53,68 @@
python grpc_main_client_mic.py --host $server_ip --port 10108
```
+The `grpc_main_client_mic.py` follows the [original design] (https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/grpc#workflow-in-desgin) by sending audio_data with chunks. If you want to send audio_data in one request, here is an example:
+
+```
+# go to ../python/grpc to find this package
+import paraformer_pb2
+
+
+class RecognizeStub:
+ def __init__(self, channel):
+ self.Recognize = channel.stream_stream(
+ '/paraformer.ASR/Recognize',
+ request_serializer=paraformer_pb2.Request.SerializeToString,
+ response_deserializer=paraformer_pb2.Response.FromString,
+ )
+
+
+async def send(channel, data, speaking, isEnd):
+ stub = RecognizeStub(channel)
+ req = paraformer_pb2.Request()
+ if data:
+ req.audio_data = data
+ req.user = 'zz'
+ req.language = 'zh-CN'
+ req.speaking = speaking
+ req.isEnd = isEnd
+ q = queue.SimpleQueue()
+ q.put(req)
+ return stub.Recognize(iter(q.get, None))
+
+# send the audio data once
+async def grpc_rec(data, grpc_uri):
+ with grpc.insecure_channel(grpc_uri) as channel:
+ b = time.time()
+ response = await send(channel, data, False, False)
+ resp = response.next()
+ text = ''
+ if 'decoding' == resp.action:
+ resp = response.next()
+ if 'finish' == resp.action:
+ text = json.loads(resp.sentence)['text']
+ response = await send(channel, None, False, True)
+ return {
+ 'text': text,
+ 'time': time.time() - b,
+ }
+
+async def test():
+ # fc = FunAsrGrpcClient('127.0.0.1', 9900)
+ # t = await fc.rec(wav.tobytes())
+ # print(t)
+ wav, _ = sf.read('z-10s.wav', dtype='int16')
+ uri = '127.0.0.1:9900'
+ res = await grpc_rec(wav.tobytes(), uri)
+ print(res)
+
+
+if __name__ == '__main__':
+ asyncio.run(test())
+
+```
+
+
## Acknowledge
1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
2. We acknowledge [DeepScience](https://www.deepscience.cn) for contributing the grpc service.
diff --git a/funasr/runtime/grpc/paraformer_server.cc b/funasr/runtime/grpc/paraformer_server.cc
index 69ce903..f2ab4e0 100644
--- a/funasr/runtime/grpc/paraformer_server.cc
+++ b/funasr/runtime/grpc/paraformer_server.cc
@@ -88,7 +88,7 @@
res.set_language(req.language());
stream->Write(res);
} else if (!req.speaking()) {
- if (client_buffers.count(req.user()) == 0) {
+ if (client_buffers.count(req.user()) == 0 && req.audio_data().size() == 0) {
Response res;
res.set_sentence(
R"({"success": true, "detail": "waiting_for_voice"})"
@@ -99,14 +99,18 @@
stream->Write(res);
}else {
auto begin_time = std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::system_clock::now().time_since_epoch()).count();
+ if (req.audio_data().size() > 0) {
+ auto& buf = client_buffers[req.user()];
+ buf.insert(buf.end(), req.audio_data().begin(), req.audio_data().end());
+ }
std::string tmp_data = this->client_buffers[req.user()];
this->clear_states(req.user());
-
+
Response res;
res.set_sentence(
R"({"success": true, "detail": "decoding data: " + std::to_string(tmp_data.length()) + " bytes"})"
);
- int data_len_int = tmp_data.length();
+ int data_len_int = tmp_data.length();
std::string data_len = std::to_string(data_len_int);
std::stringstream ss;
ss << R"({"success": true, "detail": "decoding data: )" << data_len << R"( bytes")" << R"("})";
@@ -129,18 +133,18 @@
res.set_user(req.user());
res.set_action("finish");
res.set_language(req.language());
-
-
-
+
+
+
stream->Write(res);
}
else {
- RPASR_RESULT Result= RapidAsrRecogPCMBuffer(AsrHanlde, tmp_data.c_str(), data_len_int, RASR_NONE, NULL);
+ RPASR_RESULT Result= RapidAsrRecogPCMBuffer(AsrHanlde, tmp_data.c_str(), data_len_int, RASR_NONE, NULL);
std::string asr_result = ((RPASR_RECOG_RESULT*)Result)->msg;
auto end_time = std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::system_clock::now().time_since_epoch()).count();
std::string delay_str = std::to_string(end_time - begin_time);
-
+
std::cout << "user: " << req.user() << " , delay(ms): " << delay_str << ", text: " << asr_result << std::endl;
Response res;
std::stringstream ss;
@@ -150,8 +154,8 @@
res.set_user(req.user());
res.set_action("finish");
res.set_language(req.language());
-
-
+
+
stream->Write(res);
}
}
@@ -165,7 +169,7 @@
res.set_language(req.language());
stream->Write(res);
}
- }
+ }
return Status::OK;
}
--
Gitblit v1.9.1