1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
|
# ------------------------------------
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
# ------------------------------------
import os
import pytest
import pathlib
import uuid
from devtools_testutils import AzureRecordedTestCase
from conftest import WHISPER_AZURE, OPENAI, PREVIEW, GA, configure_async, TTS_OPENAI, TTS_AZURE
audio_test_file = pathlib.Path(__file__).parent / "./assets/hello.m4a"
audio_long_test_file = pathlib.Path(__file__).parent / "./assets/wikipediaOcelot.wav"
@pytest.mark.live_test_only
class TestAudioAsync(AzureRecordedTestCase):
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize(
"api_type, api_version",
[(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")]
)
async def test_transcribe(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.transcriptions.create(
file=open(audio_test_file, "rb"),
**kwargs,
)
assert result.text == "Hello."
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_transcribe_raw(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.transcriptions.create(
# file=open(audio_test_file, "rb").read(),
# use file tuple for now
file=("hello.m4a", open(audio_test_file, "rb").read(), "application/octet-stream"),
**kwargs,
)
assert result.text == "Hello."
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize(
"api_type, api_version",
[(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")]
)
async def test_translate(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.translations.create(
file=open(audio_test_file, "rb"),
**kwargs,
)
assert result.text == "Hello."
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_translate_raw(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.translations.create(
# file=open(audio_test_file, "rb").read(),
# use file tuple for now
file=("hello.m4a", open(audio_test_file, "rb").read(), "application/octet-stream"),
**kwargs,
)
assert result.text == "Hello."
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_transcribe_verbose(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.transcriptions.create(
file=open(audio_long_test_file, "rb"),
response_format="verbose_json",
**kwargs,
)
assert result.text == "The ocelot, Lepardus paradalis, is a small wild cat native to the southwestern " \
"United States, Mexico, and Central and South America. This medium-sized cat is characterized by " \
"solid black spots and streaks on its coat, round ears, and white neck and undersides. It weighs " \
"between 8 and 15.5 kilograms, 18 and 34 pounds, and reaches 40 to 50 centimeters – 16 to 20 inches " \
"– at the shoulders. It was first described by Carl Linnaeus in 1758. Two subspecies are recognized, " \
"L. p. paradalis and L. p. mitis. Typically active during twilight and at night, the ocelot tends to " \
"be solitary and territorial. It is efficient at climbing, leaping, and swimming. It preys on small " \
"terrestrial mammals such as armadillo, opossum, and lagomorphs."
assert result.task == "transcribe"
assert result.language == "english"
assert result.duration == 56.25
for segment in result.segments:
assert segment.id is not None
assert segment.seek is not None
assert segment.start is not None
assert segment.end is not None
assert segment.text is not None
assert segment.tokens is not None
assert segment.temperature is not None
assert segment.avg_logprob is not None
assert segment.compression_ratio is not None
assert segment.no_speech_prob is not None
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_transcribe_text(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.transcriptions.create(
file=open(audio_test_file, "rb"),
response_format="text",
**kwargs,
)
assert result == "Hello.\n"
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_transcribe_srt(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.transcriptions.create(
file=open(audio_test_file, "rb"),
response_format="srt",
**kwargs,
)
assert result == "1\n00:00:00,000 --> 00:00:02,000\nHello.\n\n\n"
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_transcribe_vtt(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.transcriptions.create(
file=open(audio_test_file, "rb"),
response_format="vtt",
**kwargs,
)
assert result == "WEBVTT\n\n00:00:00.000 --> 00:00:02.000\nHello.\n\n"
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_translate_verbose(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.translations.create(
file=open(audio_long_test_file, "rb"),
response_format="verbose_json",
**kwargs,
)
assert result.text == "The ocelot, Lepardus paradalis, is a small wild cat native to the southwestern " \
"United States, Mexico, and Central and South America. This medium-sized cat is characterized by " \
"solid black spots and streaks on its coat, round ears, and white neck and undersides. It weighs " \
"between 8 and 15.5 kilograms, 18 and 34 pounds, and reaches 40 to 50 centimeters – 16 to 20 inches " \
"– at the shoulders. It was first described by Carl Linnaeus in 1758. Two subspecies are recognized, " \
"L. p. paradalis and L. p. mitis. Typically active during twilight and at night, the ocelot tends to " \
"be solitary and territorial. It is efficient at climbing, leaping, and swimming. It preys on small " \
"terrestrial mammals such as armadillo, opossum, and lagomorphs."
assert result.task == "translate"
assert result.language == "english"
assert result.duration == 56.25
for segment in result.segments:
assert segment.id is not None
assert segment.seek is not None
assert segment.start is not None
assert segment.end is not None
assert segment.text is not None
assert segment.tokens is not None
assert segment.temperature is not None
assert segment.avg_logprob is not None
assert segment.compression_ratio is not None
assert segment.no_speech_prob is not None
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_translate_text(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.translations.create(
file=open(audio_test_file, "rb"),
response_format="text",
**kwargs,
)
assert result == "Hello.\n"
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_translate_srt(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.translations.create(
file=open(audio_test_file, "rb"),
response_format="srt",
**kwargs,
)
assert result == "1\n00:00:00,000 --> 00:00:02,000\nHello.\n\n\n"
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_translate_vtt(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.translations.create(
file=open(audio_test_file, "rb"),
response_format="vtt",
**kwargs,
)
assert result == "WEBVTT\n\n00:00:00.000 --> 00:00:02.000\nHello.\n\n"
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_transcribe_options(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.transcriptions.create(
file=open(audio_test_file, "rb"),
temperature=0,
language="en",
prompt="Transcribe the text exactly as spoken.",
**kwargs,
)
assert result.text == "Hello"
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(WHISPER_AZURE, GA), (WHISPER_AZURE, PREVIEW), (OPENAI, "v1")])
async def test_translate_options(self, client_async, api_type, api_version, **kwargs):
result = await client_async.audio.translations.create(
file=open(audio_test_file, "rb"),
temperature=0,
prompt="Translate the text exactly as spoken.",
**kwargs,
)
assert result.text == "Hello"
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize(
"api_type, api_version",
[(TTS_AZURE, PREVIEW), (TTS_OPENAI, "v1")]
)
async def test_tts(self, client_async, api_type, api_version, **kwargs):
speech_file_path = pathlib.Path(__file__).parent / f"{uuid.uuid4()}.mp3"
try:
response = await client_async.audio.speech.create(
voice="alloy",
input="The quick brown fox jumped over the lazy dog.",
**kwargs,
)
assert response.encoding
assert response.content
assert response.text
response.write_to_file(speech_file_path)
finally:
os.remove(speech_file_path)
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(TTS_AZURE, PREVIEW), (TTS_OPENAI, "v1")])
async def test_tts_hd(self, client_async, api_type, api_version, **kwargs):
async with client_async.audio.speech.with_streaming_response.create(
voice="echo",
input="The quick brown fox jumped over the lazy dog.",
model="tts-1-hd"
) as response:
await response.read()
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(TTS_AZURE, PREVIEW), (TTS_OPENAI, "v1")])
async def test_tts_response_format(self, client_async, api_type, api_version, **kwargs):
speech_file_path = pathlib.Path(__file__).parent / f"{uuid.uuid4()}.flac"
try:
response = await client_async.audio.speech.create(
voice="fable",
input="The quick brown fox jumped over the lazy dog.",
response_format="flac",
**kwargs
)
assert response.encoding
assert response.content
assert response.text
await response.astream_to_file(speech_file_path) # deprecated
finally:
os.remove(speech_file_path)
@configure_async
@pytest.mark.asyncio
@pytest.mark.parametrize("api_type, api_version", [(TTS_AZURE, PREVIEW), (TTS_OPENAI, "v1")])
async def test_tts_speed(self, client_async, api_type, api_version, **kwargs):
speech_file_path = pathlib.Path(__file__).parent / f"{uuid.uuid4()}.mp3"
try:
response = await client_async.audio.speech.create(
voice="onyx",
input="The quick brown fox jumped over the lazy dog.",
speed=3.0,
**kwargs
)
assert response.encoding
assert response.content
assert response.text
response.write_to_file(speech_file_path)
finally:
os.remove(speech_file_path)
|
