Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Commit 67e3151

Browse filesBrowse files
nitsanshaiNitsan Shai
nitsanshai
and
Nitsan Shai
authored
samples: Code samples for Speech-to-Text V2 (#460)
Co-authored-by: Nitsan Shai <nshai@google.com>
1 parent 31fa496 commit 67e3151
Copy full SHA for 67e3151
Expand file treeCollapse file tree

17 files changed

+882
-4
lines changed

‎google-cloud-speech/samples/snippets/adaptation_v2_custom_class_reference.py

Copy file name to clipboard
+92Lines changed: 92 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,92 @@
1+
# Copyright 2022 Google Inc.
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
16+
# [START speech_adaptation_v2_custom_class_reference]
17+
import io
18+
19+
from google.cloud.speech_v2 import SpeechClient
20+
from google.cloud.speech_v2.types import cloud_speech
21+
22+
23+
def adaptation_v2_custom_class_reference(project_id, recognizer_id, phrase_set_id, custom_class_id, audio_file):
24+
# Instantiates a client
25+
client = SpeechClient()
26+
27+
request = cloud_speech.CreateRecognizerRequest(
28+
parent=f"projects/{project_id}/locations/global",
29+
recognizer_id=recognizer_id,
30+
recognizer=cloud_speech.Recognizer(
31+
language_codes=["en-US"], model="latest_short"
32+
),
33+
)
34+
35+
# Creates a Recognizer
36+
operation = client.create_recognizer(request=request)
37+
recognizer = operation.result()
38+
39+
# Reads a file as bytes
40+
with io.open(audio_file, "rb") as f:
41+
content = f.read()
42+
43+
# Create a persistent CustomClass to reference in phrases
44+
request = cloud_speech.CreateCustomClassRequest(
45+
parent=f"projects/{project_id}/locations/global",
46+
custom_class_id=custom_class_id,
47+
custom_class=cloud_speech.CustomClass(items=[{"value": "Keem"}]))
48+
49+
operation = client.create_custom_class(request=request)
50+
custom_class = operation.result()
51+
52+
# Create a persistent PhraseSet to reference in a recognition request
53+
request = cloud_speech.CreatePhraseSetRequest(
54+
parent=f"projects/{project_id}/locations/global",
55+
phrase_set_id=phrase_set_id,
56+
phrase_set=cloud_speech.PhraseSet(phrases=[{"value": f"${{{custom_class.name}}}", "boost": 20}]))
57+
58+
operation = client.create_phrase_set(request=request)
59+
phrase_set = operation.result()
60+
61+
# Add a reference of the PhraseSet into the recognition request
62+
adaptation = cloud_speech.SpeechAdaptation(
63+
phrase_sets=[
64+
cloud_speech.SpeechAdaptation.AdaptationPhraseSet(
65+
phrase_set=phrase_set.name
66+
)
67+
]
68+
)
69+
config = cloud_speech.RecognitionConfig(
70+
auto_decoding_config={}, adaptation=adaptation
71+
)
72+
73+
print(custom_class)
74+
print(phrase_set)
75+
print(config)
76+
77+
request = cloud_speech.RecognizeRequest(
78+
recognizer=recognizer.name, config=config, content=content
79+
)
80+
81+
# Transcribes the audio into text
82+
response = client.recognize(request=request)
83+
84+
for result in response.results:
85+
print("Transcript: {}".format(result.alternatives[0].transcript))
86+
87+
return response
88+
# [END speech_adaptation_v2_custom_class_reference]
89+
90+
91+
if __name__ == "__main__":
92+
adaptation_v2_custom_class_reference()

‎google-cloud-speech/samples/snippets/adaptation_v2_custom_class_reference_test.py

Copy file name to clipboard
+70Lines changed: 70 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,70 @@
1+
# Copyright 2022, Google, Inc.
2+
# Licensed under the Apache License, Version 2.0 (the "License");
3+
# you may not use this file except in compliance with the License.
4+
# You may obtain a copy of the License at
5+
#
6+
# http://www.apache.org/licenses/LICENSE-2.0
7+
#
8+
# Unless required by applicable law or agreed to in writing, software
9+
# distributed under the License is distributed on an "AS IS" BASIS,
10+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
11+
# See the License for the specific language governing permissions and
12+
# limitations under the License.
13+
14+
import os
15+
import re
16+
from uuid import uuid4
17+
18+
from google.cloud.speech_v2 import SpeechClient
19+
from google.cloud.speech_v2.types import cloud_speech
20+
21+
import adaptation_v2_custom_class_reference
22+
23+
RESOURCES = os.path.join(os.path.dirname(__file__), "resources")
24+
25+
26+
def delete_recognizer(name):
27+
client = SpeechClient()
28+
request = cloud_speech.DeleteRecognizerRequest(name=name)
29+
client.delete_recognizer(request=request)
30+
31+
32+
def delete_phrase_set(name):
33+
client = SpeechClient()
34+
request = cloud_speech.DeletePhraseSetRequest(name=name)
35+
client.delete_phrase_set(request=request)
36+
37+
38+
def delete_custom_class(name):
39+
client = SpeechClient()
40+
request = cloud_speech.DeleteCustomClassRequest(name=name)
41+
client.delete_custom_class(request=request)
42+
43+
44+
def test_adaptation_v2_custom_class_reference(capsys):
45+
project_id = os.getenv("GOOGLE_CLOUD_PROJECT")
46+
47+
recognizer_id = "recognizer-" + str(uuid4())
48+
phrase_set_id = "phrase-set-" + str(uuid4())
49+
custom_class_id = "custom-class-" + str(uuid4())
50+
response = adaptation_v2_custom_class_reference.adaptation_v2_custom_class_reference(
51+
project_id, recognizer_id, phrase_set_id, custom_class_id, os.path.join(RESOURCES, "baby_keem.wav")
52+
)
53+
54+
assert re.search(
55+
r"play Baby Keem",
56+
response.results[0].alternatives[0].transcript,
57+
re.DOTALL | re.I,
58+
)
59+
60+
delete_recognizer(
61+
f"projects/{project_id}/locations/global/recognizers/{recognizer_id}"
62+
)
63+
64+
delete_phrase_set(
65+
f"projects/{project_id}/locations/global/phraseSets/{phrase_set_id}"
66+
)
67+
68+
delete_custom_class(
69+
f"projects/{project_id}/locations/global/customClasses/{custom_class_id}"
70+
)

‎google-cloud-speech/samples/snippets/adaptation_v2_inline_custom_class.py

Copy file name to clipboard
+73Lines changed: 73 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,73 @@
1+
# Copyright 2022 Google Inc.
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
16+
# [START speech_adaptation_v2_inline_custom_class]
17+
import io
18+
19+
from google.cloud.speech_v2 import SpeechClient
20+
from google.cloud.speech_v2.types import cloud_speech
21+
22+
23+
def adaptation_v2_inline_custom_class(project_id, recognizer_id, audio_file):
24+
# Instantiates a client
25+
client = SpeechClient()
26+
27+
request = cloud_speech.CreateRecognizerRequest(
28+
parent=f"projects/{project_id}/locations/global",
29+
recognizer_id=recognizer_id,
30+
recognizer=cloud_speech.Recognizer(
31+
language_codes=["en-US"], model="latest_short"
32+
),
33+
)
34+
35+
# Creates a Recognizer
36+
operation = client.create_recognizer(request=request)
37+
recognizer = operation.result()
38+
39+
# Reads a file as bytes
40+
with io.open(audio_file, "rb") as f:
41+
content = f.read()
42+
43+
# Build inline phrase set to produce a more accurate transcript
44+
phrase_set = cloud_speech.PhraseSet(phrases=[{"value": "${keem}", "boost": 20}])
45+
custom_class = cloud_speech.CustomClass(name="keem", items=[{"value": "Keem"}])
46+
adaptation = cloud_speech.SpeechAdaptation(
47+
phrase_sets=[
48+
cloud_speech.SpeechAdaptation.AdaptationPhraseSet(
49+
inline_phrase_set=phrase_set
50+
)
51+
],
52+
custom_classes=[custom_class]
53+
)
54+
config = cloud_speech.RecognitionConfig(
55+
auto_decoding_config={}, adaptation=adaptation
56+
)
57+
58+
request = cloud_speech.RecognizeRequest(
59+
recognizer=recognizer.name, config=config, content=content
60+
)
61+
62+
# Transcribes the audio into text
63+
response = client.recognize(request=request)
64+
65+
for result in response.results:
66+
print("Transcript: {}".format(result.alternatives[0].transcript))
67+
68+
return response
69+
# [END speech_adaptation_v2_inline_custom_class]
70+
71+
72+
if __name__ == "__main__":
73+
adaptation_v2_inline_custom_class()

‎google-cloud-speech/samples/snippets/adaptation_v2_inline_custom_class_test.py

Copy file name to clipboard
+48Lines changed: 48 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,48 @@
1+
# Copyright 2022, Google, Inc.
2+
# Licensed under the Apache License, Version 2.0 (the "License");
3+
# you may not use this file except in compliance with the License.
4+
# You may obtain a copy of the License at
5+
#
6+
# http://www.apache.org/licenses/LICENSE-2.0
7+
#
8+
# Unless required by applicable law or agreed to in writing, software
9+
# distributed under the License is distributed on an "AS IS" BASIS,
10+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
11+
# See the License for the specific language governing permissions and
12+
# limitations under the License.
13+
14+
import os
15+
import re
16+
from uuid import uuid4
17+
18+
from google.cloud.speech_v2 import SpeechClient
19+
from google.cloud.speech_v2.types import cloud_speech
20+
21+
import adaptation_v2_inline_custom_class
22+
23+
RESOURCES = os.path.join(os.path.dirname(__file__), "resources")
24+
25+
26+
def delete_recognizer(name):
27+
client = SpeechClient()
28+
request = cloud_speech.DeleteRecognizerRequest(name=name)
29+
client.delete_recognizer(request=request)
30+
31+
32+
def test_adaptation_v2_inline_custom_class(capsys):
33+
project_id = os.getenv("GOOGLE_CLOUD_PROJECT")
34+
35+
recognizer_id = "recognizer-" + str(uuid4())
36+
response = adaptation_v2_inline_custom_class.adaptation_v2_inline_custom_class(
37+
project_id, recognizer_id, os.path.join(RESOURCES, "baby_keem.wav")
38+
)
39+
40+
assert re.search(
41+
r"play Baby Keem",
42+
response.results[0].alternatives[0].transcript,
43+
re.DOTALL | re.I,
44+
)
45+
46+
delete_recognizer(
47+
f"projects/{project_id}/locations/global/recognizers/{recognizer_id}"
48+
)

‎google-cloud-speech/samples/snippets/adaptation_v2_inline_phrase_set.py

Copy file name to clipboard
+71Lines changed: 71 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,71 @@
1+
# Copyright 2022 Google Inc.
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
16+
# [START speech_adaptation_v2_inline_phrase_set]
17+
import io
18+
19+
from google.cloud.speech_v2 import SpeechClient
20+
from google.cloud.speech_v2.types import cloud_speech
21+
22+
23+
def adaptation_v2_inline_phrase_set(project_id, recognizer_id, audio_file):
24+
# Instantiates a client
25+
client = SpeechClient()
26+
27+
request = cloud_speech.CreateRecognizerRequest(
28+
parent=f"projects/{project_id}/locations/global",
29+
recognizer_id=recognizer_id,
30+
recognizer=cloud_speech.Recognizer(
31+
language_codes=["en-US"], model="latest_short"
32+
),
33+
)
34+
35+
# Creates a Recognizer
36+
operation = client.create_recognizer(request=request)
37+
recognizer = operation.result()
38+
39+
# Reads a file as bytes
40+
with io.open(audio_file, "rb") as f:
41+
content = f.read()
42+
43+
# Build inline phrase set to produce a more accurate transcript
44+
phrase_set = cloud_speech.PhraseSet(phrases=[{"value": "Keem", "boost": 10}])
45+
adaptation = cloud_speech.SpeechAdaptation(
46+
phrase_sets=[
47+
cloud_speech.SpeechAdaptation.AdaptationPhraseSet(
48+
inline_phrase_set=phrase_set
49+
)
50+
]
51+
)
52+
config = cloud_speech.RecognitionConfig(
53+
auto_decoding_config={}, adaptation=adaptation
54+
)
55+
56+
request = cloud_speech.RecognizeRequest(
57+
recognizer=recognizer.name, config=config, content=content
58+
)
59+
60+
# Transcribes the audio into text
61+
response = client.recognize(request=request)
62+
63+
for result in response.results:
64+
print("Transcript: {}".format(result.alternatives[0].transcript))
65+
66+
return response
67+
# [END speech_adaptation_v2_inline_phrase_set]
68+
69+
70+
if __name__ == "__main__":
71+
adaptation_v2_inline_phrase_set()

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.