feat(api): Add transcribe response format request parameter & adjust STT backends (#8318)

* WIP response format implementation for audio transcriptions

(cherry picked from commit e271dd764bbc13846accf3beb8b6522153aa276f)
Signed-off-by: Andres Smith <andressmithdev@pm.me>

* Rework transcript response_format and add more formats

(cherry picked from commit 6a93a8f63e2ee5726bca2980b0c9cf4ef8b7aeb8)
Signed-off-by: Andres Smith <andressmithdev@pm.me>

* Add test and replace go-openai package with official openai go client

(cherry picked from commit f25d1a04e46526429c89db4c739e1e65942ca893)
Signed-off-by: Andres Smith <andressmithdev@pm.me>

* Fix faster-whisper backend and refactor transcription formatting to also work on CLI

Signed-off-by: Andres Smith <andressmithdev@pm.me>
(cherry picked from commit 69a93977d5e113eb7172bd85a0f918592d3d2168)
Signed-off-by: Andres Smith <andressmithdev@pm.me>

---------

Signed-off-by: Andres Smith <andressmithdev@pm.me>
Co-authored-by: nanoandrew4 <nanoandrew4@gmail.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Andres
2026-02-01 17:33:17 +01:00
committed by GitHub
parent 397f7f0862
commit b6459ddd57
18 changed files with 353 additions and 184 deletions

View File

@@ -40,7 +40,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
device = "mps"
try:
print("Preparing models, please wait", file=sys.stderr)
self.model = WhisperModel(request.Model, device=device, compute_type="float16")
self.model = WhisperModel(request.Model, device=device, compute_type="default")
except Exception as err:
return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
# Implement your logic here for the LoadModel service
@@ -55,11 +55,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
id = 0
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
resultSegments.append(backend_pb2.TranscriptSegment(id=id, start=segment.start, end=segment.end, text=segment.text))
resultSegments.append(backend_pb2.TranscriptSegment(id=id, start=int(segment.start)*1e9, end=int(segment.end)*1e9, text=segment.text))
text += segment.text
id += 1
id += 1
except Exception as err:
print(f"Unexpected {err=}, {type(err)=}", file=sys.stderr)
raise err
return backend_pb2.TranscriptResult(segments=resultSegments, text=text)