interhumanai 3.2.1__tar.gz → 3.3.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {interhumanai-3.2.1 → interhumanai-3.3.0}/CHANGELOG.md +11 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/PKG-INFO +8 -4
- {interhumanai-3.2.1 → interhumanai-3.3.0}/README.md +7 -3
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/_version.py +1 -1
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/types.py +13 -1
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/upload.py +9 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/.gitignore +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/LICENSE +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/pyproject.toml +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/__init__.py +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/_http.py +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/_sdk_metadata.py +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/_session_socket.py +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/auth.py +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/client.py +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/config.py +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/errors.py +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/py.typed +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/realtime.py +0 -0
- {interhumanai-3.2.1 → interhumanai-3.3.0}/src/interhumanai/stream.py +0 -0
|
@@ -5,6 +5,17 @@ All notable changes to `interhumanai` are documented here. The package follows
|
|
|
5
5
|
the TypeScript SDK (`@interhumanai/sdk`): both packages always carry the same
|
|
6
6
|
version and release together.
|
|
7
7
|
|
|
8
|
+
## 3.3.0
|
|
9
|
+
|
|
10
|
+
- Added the ``language`` argument to ``UploadClient.submit``: the spoken
|
|
11
|
+
language as an ISO 639 code such as ``"en"``. An ``UploadModel.INTER_2_DEEP``
|
|
12
|
+
job's transcript is then made in that language rather than a detected one.
|
|
13
|
+
Any other model raises ``ih4005``.
|
|
14
|
+
- Added ``UploadJobTranscript.language_source`` (``"requested"`` or
|
|
15
|
+
``"detected"``) and ``UploadJobTranscript.language_probability`` (the
|
|
16
|
+
recognizer's 0–1 confidence in a detected language, where it reports one).
|
|
17
|
+
A detected ``language`` is best-effort.
|
|
18
|
+
|
|
8
19
|
## 3.2.1
|
|
9
20
|
|
|
10
21
|
- Documentation only: when no speaker could be identified as on camera, the
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: interhumanai
|
|
3
|
-
Version: 3.
|
|
3
|
+
Version: 3.3.0
|
|
4
4
|
Summary: First-party Python SDK for the Interhuman API: upload and stream social-signal analysis.
|
|
5
5
|
Project-URL: Homepage, https://docs.interhuman.ai
|
|
6
6
|
Project-URL: Repository, https://github.com/interhuman-core/interhuman-api
|
|
@@ -172,11 +172,15 @@ else:
|
|
|
172
172
|
(`text`, `start`, `end`, `speaker`, `speaker_role`) and the speaker
|
|
173
173
|
segments. Check `transcript.status` first: `FAILED` means no transcript
|
|
174
174
|
could be produced, carries `error`, and leaves the job completed.
|
|
175
|
+
`transcript.language_source` says whether `language` is the one you named
|
|
176
|
+
(`"requested"`) or the recognizer's guess (`"detected"`), which is
|
|
177
|
+
best-effort: pass `language="en"` (any ISO 639 code) to `submit` wherever
|
|
178
|
+
you know the spoken language. Only `INTER_2_DEEP` takes it.
|
|
175
179
|
`VISUAL_CUES`, `LEXICAL_CUES` and `SPEECH_CUES` add `visual_cues`,
|
|
176
180
|
`lexical_cues` and `speech_cues`: timestamped cue lists, each with its own
|
|
177
|
-
`status`.
|
|
178
|
-
|
|
179
|
-
|
|
181
|
+
`status`. A deployment serves each list only where it is enabled; a submit
|
|
182
|
+
that names a list the deployment does not serve is refused with `ih1003`. Without a flag the result has no
|
|
183
|
+
such section.
|
|
180
184
|
- `get_job(job_id)` — one status read. Raises `InterhumanAPIError` with
|
|
181
185
|
`error_id` `ih4021` once the job has expired (`job.expires_at`).
|
|
182
186
|
- `wait_for_job(job_id, timeout=None, poll_interval=2.0)` — returns the
|
|
@@ -146,11 +146,15 @@ else:
|
|
|
146
146
|
(`text`, `start`, `end`, `speaker`, `speaker_role`) and the speaker
|
|
147
147
|
segments. Check `transcript.status` first: `FAILED` means no transcript
|
|
148
148
|
could be produced, carries `error`, and leaves the job completed.
|
|
149
|
+
`transcript.language_source` says whether `language` is the one you named
|
|
150
|
+
(`"requested"`) or the recognizer's guess (`"detected"`), which is
|
|
151
|
+
best-effort: pass `language="en"` (any ISO 639 code) to `submit` wherever
|
|
152
|
+
you know the spoken language. Only `INTER_2_DEEP` takes it.
|
|
149
153
|
`VISUAL_CUES`, `LEXICAL_CUES` and `SPEECH_CUES` add `visual_cues`,
|
|
150
154
|
`lexical_cues` and `speech_cues`: timestamped cue lists, each with its own
|
|
151
|
-
`status`.
|
|
152
|
-
|
|
153
|
-
|
|
155
|
+
`status`. A deployment serves each list only where it is enabled; a submit
|
|
156
|
+
that names a list the deployment does not serve is refused with `ih1003`. Without a flag the result has no
|
|
157
|
+
such section.
|
|
154
158
|
- `get_job(job_id)` — one status read. Raises `InterhumanAPIError` with
|
|
155
159
|
`error_id` `ih4021` once the job has expired (`job.expires_at`).
|
|
156
160
|
- `wait_for_job(job_id, timeout=None, poll_interval=2.0)` — returns the
|
|
@@ -444,7 +444,17 @@ class UploadJobTranscript(BaseModel):
|
|
|
444
444
|
|
|
445
445
|
Attributes:
|
|
446
446
|
status: Whether the file was transcribed.
|
|
447
|
-
language: The language
|
|
447
|
+
language: The language the speech was transcribed in, as an ISO 639
|
|
448
|
+
code. When ``language_source`` is ``"detected"`` it is the speech
|
|
449
|
+
recognizer's own guess, which is best-effort and can be wrong:
|
|
450
|
+
pass ``language`` to :meth:`UploadClient.submit` where you know it.
|
|
451
|
+
language_source: Where ``language`` came from: ``"requested"``, the
|
|
452
|
+
language the submit named, or ``"detected"``, the recognizer's
|
|
453
|
+
own guess. ``None`` when ``language`` is, or when the speech
|
|
454
|
+
service did not report it.
|
|
455
|
+
language_probability: The recognizer's confidence, from 0 to 1, in a
|
|
456
|
+
detected language. ``None`` for a requested language and wherever
|
|
457
|
+
the recognizer reports no confidence.
|
|
448
458
|
speaker_roles_status: Whether the speakers could be told apart as on
|
|
449
459
|
camera or off it: ``"mapped"`` when at least one speaker has a
|
|
450
460
|
role, ``"unmapped"`` when none could be told, ``"no_face"`` when no
|
|
@@ -462,6 +472,8 @@ class UploadJobTranscript(BaseModel):
|
|
|
462
472
|
|
|
463
473
|
status: UploadJobTranscriptStatus
|
|
464
474
|
language: str | None = None
|
|
475
|
+
language_source: str | None = None
|
|
476
|
+
language_probability: float | None = None
|
|
465
477
|
speaker_roles_status: str | None = None
|
|
466
478
|
word_timing: str | None = None
|
|
467
479
|
words: list[UploadJobTranscriptWord] = Field(default_factory=list)
|
|
@@ -127,6 +127,7 @@ class UploadClient:
|
|
|
127
127
|
model: UploadModel | str,
|
|
128
128
|
wait_seconds: int = 0,
|
|
129
129
|
include: Sequence[UploadJobIncludeFlag | IncludeFlag | str] | None = None,
|
|
130
|
+
language: str | None = None,
|
|
130
131
|
filename: str | None = None,
|
|
131
132
|
content_type: str | None = None,
|
|
132
133
|
) -> UploadJob:
|
|
@@ -174,6 +175,12 @@ class UploadClient:
|
|
|
174
175
|
:meth:`analyze` takes, so :class:`IncludeFlag` members work
|
|
175
176
|
too) for the quality block, and ``SIGNALS`` for the signal
|
|
176
177
|
list. Omit a flag for no such section.
|
|
178
|
+
language: The language spoken in the file, as a two- or
|
|
179
|
+
three-letter ISO 639 code such as ``"en"``.
|
|
180
|
+
``UploadModel.INTER_2_DEEP`` accepts it, and its transcript is
|
|
181
|
+
then made in that language. Without it the speech recognizer
|
|
182
|
+
detects the language, which is best-effort. Any other model
|
|
183
|
+
raises ``ih4005``.
|
|
177
184
|
filename: Filename reported to the API. Defaults to the path or
|
|
178
185
|
file object's name, else ``video``.
|
|
179
186
|
content_type: MIME type of the file (e.g. ``video/mp4``).
|
|
@@ -194,6 +201,8 @@ class UploadClient:
|
|
|
194
201
|
flag.value if isinstance(flag, (IncludeFlag, UploadJobIncludeFlag)) else flag
|
|
195
202
|
for flag in include
|
|
196
203
|
]
|
|
204
|
+
if language:
|
|
205
|
+
data["language"] = language
|
|
197
206
|
headers = {"Authorization": f"Bearer {token}"}
|
|
198
207
|
url = self._base_url + "/v2/upload/analyze"
|
|
199
208
|
payload = await self._request(
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|