Skip to content

[qwen2 audio] remove redundant code and update docs #36282

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

Merged
gante merged 1 commit into from
Mar 20, 2025
Merged

[qwen2 audio] remove redundant code and update docs #36282

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
17 changes: 11 additions & 6 deletions docs/source/en/model_doc/qwen2_audio.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ The Qwen2-Audio is the new model series of large audio-language models from the
* voice chat: users can freely engage in voice interactions with Qwen2-Audio without text input
* audio analysis: users could provide audio and text instructions for analysis during the interaction

It was proposed in [Qwen2-Audio Technical Report](https://arxiv.org/abs/2407.10759) by Yunfei Chu, Jin Xu, Qian Yang, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, Yuanjun Lv, Jinzheng He, Junyang Lin, Chang Zhou, Jingren Zhou.
It was proposed in [Qwen2-Audio Technical Report](https://arxiv.org/abs/2407.10759) by Yunfei Chu, Jin Xu, Qian Yang, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, Yuanjun Lv, Jinzheng He, Junyang Lin, Chang Zhou, Jingren Zhou.

The abstract from the paper is the following:

Expand Down Expand Up @@ -94,7 +94,7 @@ for message in conversation:
for ele in message["content"]:
if ele["type"] == "audio":
audios.append(librosa.load(
BytesIO(urlopen(ele['audio_url']).read()),
BytesIO(urlopen(ele['audio_url']).read()),
sr=processor.feature_extractor.sampling_rate)[0]
)

Expand All @@ -119,7 +119,7 @@ processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")
model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct", device_map="auto")

conversation = [
{'role': 'system', 'content': 'You are a helpful assistant.'},
{'role': 'system', 'content': 'You are a helpful assistant.'},
{"role": "user", "content": [
{"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/glass-breaking-151256.mp3"},
{"type": "text", "text": "What's that sound?"},
Expand All @@ -142,7 +142,7 @@ for message in conversation:
if ele["type"] == "audio":
audios.append(
librosa.load(
BytesIO(urlopen(ele['audio_url']).read()),
BytesIO(urlopen(ele['audio_url']).read()),
sr=processor.feature_extractor.sampling_rate)[0]
)

Expand Down Expand Up @@ -197,7 +197,7 @@ for conversation in conversations:
if ele["type"] == "audio":
audios.append(
librosa.load(
BytesIO(urlopen(ele['audio_url']).read()),
BytesIO(urlopen(ele['audio_url']).read()),
sr=processor.feature_extractor.sampling_rate)[0]
)

Expand All @@ -215,14 +215,19 @@ response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_

[[autodoc]] Qwen2AudioConfig

## Qwen2AudioConfig
## Qwen2AudioEncoderConfig

[[autodoc]] Qwen2AudioEncoderConfig

## Qwen2AudioProcessor

[[autodoc]] Qwen2AudioProcessor

## Qwen2AudioEncoder

[[autodoc]] Qwen2AudioEncoder
- forward

## Qwen2AudioForConditionalGeneration

[[autodoc]] Qwen2AudioForConditionalGeneration
Expand Down
Loading