Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Whisper: fix asr pipeline with seq2seq assistant model #30726

Closed
wants to merge 4 commits into from
Closed

Whisper: fix asr pipeline with seq2seq assistant model #30726

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0f38577
fix asr pipeline with seq2seq assistant model
gante May 9, 2024
705b2e8
[run slow] whisper
gante May 9, 2024
0c90dc5
fix wav2vec pipeline test
gante May 9, 2024
c1c2f43
[run slow] whisper
gante May 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 1 addition & 6 deletions src/transformers/pipelines/automatic_speech_recognition.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -468,7 +468,6 @@ def _forward(self, model_inputs, return_timestamps=False, **generate_kwargs):
raise ValueError("segment_size must be used only when stride is None")

if self.type in {"seq2seq", "seq2seq_whisper"}:
encoder = self.model.get_encoder()
# Consume values so we can let extra information flow freely through
# the pipeline (important for `partial` in microphone)
if "input_features" in model_inputs:
Expand Down Expand Up @@ -500,12 +499,8 @@ def _forward(self, model_inputs, return_timestamps=False, **generate_kwargs):
else:
generate_kwargs["num_frames"] = segment_size[0] // self.feature_extractor.hop_length

if self.type == "seq2seq_whisper" and inputs.shape[-1] > self.feature_extractor.nb_max_frames:
generate_kwargs["input_features"] = inputs
else:
generate_kwargs["encoder_outputs"] = encoder(inputs, attention_mask=attention_mask)

tokens = self.model.generate(
inputs,
attention_mask=attention_mask,
**generate_kwargs,
)
Expand Down
Loading