rrevo commited on
Commit
1ba4a0c
·
1 Parent(s): 6e090f6
client/pdm.lock CHANGED
@@ -5,7 +5,7 @@
5
  groups = ["default"]
6
  strategy = ["cross_platform"]
7
  lock_version = "4.4"
8
- content_hash = "sha256:89d7b04abcb48301359df73888824b63edc037d5a7cdbdfa64bf22c7352dc2a9"
9
 
10
  [[package]]
11
  name = "accelerate"
@@ -26,6 +26,20 @@ files = [
26
  {file = "accelerate-0.26.1.tar.gz", hash = "sha256:bf63716b6bd9460d87da970cf4d833abb824ca0aa633be36b741e63a1b504f89"},
27
  ]
28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  [[package]]
30
  name = "certifi"
31
  version = "2023.11.17"
@@ -106,6 +120,47 @@ files = [
106
  {file = "fsspec-2023.12.2.tar.gz", hash = "sha256:8548d39e8810b59c38014934f6b31e57f40c1b20f911f4cc2b85389c7e9bf0cb"},
107
  ]
108
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  [[package]]
110
  name = "huggingface-hub"
111
  version = "0.20.2"
@@ -526,6 +581,16 @@ files = [
526
  {file = "safetensors-0.4.1.tar.gz", hash = "sha256:2304658e6ada81a5223225b4efe84748e760c46079bffedf7e321763cafb36c9"},
527
  ]
528
 
 
 
 
 
 
 
 
 
 
 
529
  [[package]]
530
  name = "speechrecognition"
531
  version = "3.10.1"
 
5
  groups = ["default"]
6
  strategy = ["cross_platform"]
7
  lock_version = "4.4"
8
+ content_hash = "sha256:cb77a02fed8fa68d3cdbb9acec8b4eb8cd20809e92c3fb5f5195bcb1e80fedb7"
9
 
10
  [[package]]
11
  name = "accelerate"
 
26
  {file = "accelerate-0.26.1.tar.gz", hash = "sha256:bf63716b6bd9460d87da970cf4d833abb824ca0aa633be36b741e63a1b504f89"},
27
  ]
28
 
29
+ [[package]]
30
+ name = "anyio"
31
+ version = "4.2.0"
32
+ requires_python = ">=3.8"
33
+ summary = "High level compatibility layer for multiple asynchronous event loop implementations"
34
+ dependencies = [
35
+ "idna>=2.8",
36
+ "sniffio>=1.1",
37
+ ]
38
+ files = [
39
+ {file = "anyio-4.2.0-py3-none-any.whl", hash = "sha256:745843b39e829e108e518c489b31dc757de7d2131d53fac32bd8df268227bfee"},
40
+ {file = "anyio-4.2.0.tar.gz", hash = "sha256:e1875bb4b4e2de1669f4bc7869b6d3f54231cdced71605e6e64c9be77e3be50f"},
41
+ ]
42
+
43
  [[package]]
44
  name = "certifi"
45
  version = "2023.11.17"
 
120
  {file = "fsspec-2023.12.2.tar.gz", hash = "sha256:8548d39e8810b59c38014934f6b31e57f40c1b20f911f4cc2b85389c7e9bf0cb"},
121
  ]
122
 
123
+ [[package]]
124
+ name = "h11"
125
+ version = "0.14.0"
126
+ requires_python = ">=3.7"
127
+ summary = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
128
+ files = [
129
+ {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
130
+ {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
131
+ ]
132
+
133
+ [[package]]
134
+ name = "httpcore"
135
+ version = "1.0.2"
136
+ requires_python = ">=3.8"
137
+ summary = "A minimal low-level HTTP client."
138
+ dependencies = [
139
+ "certifi",
140
+ "h11<0.15,>=0.13",
141
+ ]
142
+ files = [
143
+ {file = "httpcore-1.0.2-py3-none-any.whl", hash = "sha256:096cc05bca73b8e459a1fc3dcf585148f63e534eae4339559c9b8a8d6399acc7"},
144
+ {file = "httpcore-1.0.2.tar.gz", hash = "sha256:9fc092e4799b26174648e54b74ed5f683132a464e95643b226e00c2ed2fa6535"},
145
+ ]
146
+
147
+ [[package]]
148
+ name = "httpx"
149
+ version = "0.26.0"
150
+ requires_python = ">=3.8"
151
+ summary = "The next generation HTTP client."
152
+ dependencies = [
153
+ "anyio",
154
+ "certifi",
155
+ "httpcore==1.*",
156
+ "idna",
157
+ "sniffio",
158
+ ]
159
+ files = [
160
+ {file = "httpx-0.26.0-py3-none-any.whl", hash = "sha256:8915f5a3627c4d47b73e8202457cb28f1266982d1159bd5779d86a80c0eab1cd"},
161
+ {file = "httpx-0.26.0.tar.gz", hash = "sha256:451b55c30d5185ea6b23c2c793abf9bb237d2a7dfb901ced6ff69ad37ec1dfaf"},
162
+ ]
163
+
164
  [[package]]
165
  name = "huggingface-hub"
166
  version = "0.20.2"
 
581
  {file = "safetensors-0.4.1.tar.gz", hash = "sha256:2304658e6ada81a5223225b4efe84748e760c46079bffedf7e321763cafb36c9"},
582
  ]
583
 
584
+ [[package]]
585
+ name = "sniffio"
586
+ version = "1.3.0"
587
+ requires_python = ">=3.7"
588
+ summary = "Sniff out which async library your code is running under"
589
+ files = [
590
+ {file = "sniffio-1.3.0-py3-none-any.whl", hash = "sha256:eecefdce1e5bbfb7ad2eeaabf7c1eeb404d7757c379bd1f7e5cce9d8bf425384"},
591
+ {file = "sniffio-1.3.0.tar.gz", hash = "sha256:e60305c5e5d314f5389259b7f22aaa33d8f7dee49763119234af3755c55b9101"},
592
+ ]
593
+
594
  [[package]]
595
  name = "speechrecognition"
596
  version = "3.10.1"
client/pyproject.toml CHANGED
@@ -10,6 +10,7 @@ dependencies = [
10
  "PyAudio>=0.2.14",
11
  "SpeechRecognition>=3.10.1",
12
  "transformers[torch]>=4.36.2",
 
13
  ]
14
  requires-python = ">=3.11"
15
  readme = "README.md"
 
10
  "PyAudio>=0.2.14",
11
  "SpeechRecognition>=3.10.1",
12
  "transformers[torch]>=4.36.2",
13
+ "httpx>=0.26.0",
14
  ]
15
  requires-python = ">=3.11"
16
  readme = "README.md"
client/src/main.py CHANGED
@@ -1,3 +1,4 @@
 
1
  from queue import Queue
2
  import logging
3
  from datetime import UTC, datetime, timedelta
@@ -10,6 +11,9 @@ from audio_utils import get_microphone, get_speech_recognizer, get_all_audio_que
10
 
11
  logger = logging.getLogger(__name__)
12
 
 
 
 
13
  def main():
14
  recording_duration = 2
15
  sample_rate = 16000
@@ -48,7 +52,10 @@ def main():
48
 
49
  if current_audio_chunk.is_complete:
50
  serialized = pickle.dumps(current_audio_chunk.audio_array)
51
- print('chunk done', serialized)
 
 
 
52
  # text = transcribe_model.transcribe(current_audio_chunk.audio_array)
53
  # sentence = Sentence(
54
  # start_time=current_audio_chunk.start_time, end_time=current_audio_chunk.end_time, text=text
 
1
+ import httpx
2
  from queue import Queue
3
  import logging
4
  from datetime import UTC, datetime, timedelta
 
11
 
12
  logger = logging.getLogger(__name__)
13
 
14
+ TRANSCRIBING_SERVER = "http://localhost:3535/transcribe"
15
+
16
+
17
  def main():
18
  recording_duration = 2
19
  sample_rate = 16000
 
52
 
53
  if current_audio_chunk.is_complete:
54
  serialized = pickle.dumps(current_audio_chunk.audio_array)
55
+
56
+ response = httpx.post(TRANSCRIBING_SERVER, data=serialized)
57
+ print('chunk done', response.text, response.status_code)
58
+
59
  # text = transcribe_model.transcribe(current_audio_chunk.audio_array)
60
  # sentence = Sentence(
61
  # start_time=current_audio_chunk.start_time, end_time=current_audio_chunk.end_time, text=text
server/src/main.py CHANGED
@@ -10,6 +10,6 @@ def read_root():
10
  return {"status": "ok"}
11
 
12
 
13
- @app.get("/items/{item_id}")
14
- def read_item(item_id: int, q: Union[str, None] = None):
15
- return {"item_id": item_id, "q": q}
 
10
  return {"status": "ok"}
11
 
12
 
13
+ @app.post("/transcribe")
14
+ def transcribe(audio: bytes):
15
+ return {"transcribe": "hello"}