Spaces:
Sleeping
Sleeping
File size: 9,293 Bytes
2e37cc0 06a456e 2e37cc0 12bd81d 2e37cc0 c42945c 2e37cc0 4bbc7e3 2e37cc0 c42945c 2e37cc0 4bbc7e3 c1f878d 4bbc7e3 c1f878d 4bbc7e3 c1f878d 4bbc7e3 c1f878d 4bbc7e3 c1f878d 4bbc7e3 c1f878d 8fa5640 c1f878d 4bbc7e3 2e37cc0 4bbc7e3 2e37cc0 |
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 |
import gradio as gr
import modelscope_studio as mgr
import librosa
from transformers import AutoProcessor, Qwen2AudioForConditionalGeneration
from argparse import ArgumentParser
DEFAULT_CKPT_PATH = 'Qwen/Qwen2-Audio-7B-Instruct'
def _get_args():
parser = ArgumentParser()
parser.add_argument("-c", "--checkpoint-path", type=str, default=DEFAULT_CKPT_PATH,
help="Checkpoint name or path, default to %(default)r")
parser.add_argument("--cpu-only", action="store_true", help="Run demo with CPU only")
parser.add_argument("--inbrowser", action="store_true", default=False,
help="Automatically launch the interface in a new tab on the default browser.")
parser.add_argument("--server-port", type=int, default=7860,
help="Demo server port.")
parser.add_argument("--server-name", type=str, default="0.0.0.0",
help="Demo server name.")
args = parser.parse_args()
return args
def add_text(chatbot, task_history, input):
text_content = input.text
content = []
if len(input.files) > 0:
for i in input.files:
content.append({'type': 'audio', 'audio_url': i.path})
if text_content:
content.append({'type': 'text', 'text': text_content})
task_history.append({"role": "user", "content": content})
chatbot.append([{
"text": input.text,
"files": input.files,
}, None])
return chatbot, task_history, None
def add_file(chatbot, task_history, audio_file):
"""Add audio file to the chat history."""
task_history.append({"role": "user", "content": [{"audio": audio_file.name}]})
chatbot.append((f"[Audio file: {audio_file.name}]", None))
return chatbot, task_history
def reset_user_input():
"""Reset the user input field."""
return gr.Textbox.update(value='')
def reset_state(task_history):
"""Reset the chat history."""
return [], []
def regenerate(chatbot, task_history):
"""Regenerate the last bot response."""
if task_history and task_history[-1]['role'] == 'assistant':
task_history.pop()
chatbot.pop()
if task_history:
chatbot, task_history = predict(chatbot, task_history)
return chatbot, task_history
def predict(chatbot, task_history):
"""Generate a response from the model."""
print(f"{task_history=}")
print(f"{chatbot=}")
text = processor.apply_chat_template(task_history, add_generation_prompt=True, tokenize=False)
audios = []
for message in task_history:
if isinstance(message["content"], list):
for ele in message["content"]:
if ele["type"] == "audio":
audios.append(
librosa.load(ele['audio_url'], sr=processor.feature_extractor.sampling_rate)[0]
)
if len(audios)==0:
audios=None
print(f"{text=}")
print(f"{audios=}")
inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
if not _get_args().cpu_only:
inputs["input_ids"] = inputs.input_ids.to("cuda")
generate_ids = model.generate(**inputs, max_length=256)
generate_ids = generate_ids[:, inputs.input_ids.size(1):]
response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
print(f"{response=}")
task_history.append({'role': 'assistant',
'content': response})
chatbot.append((None, response)) # Add the response to chatbot
return chatbot, task_history
def _launch_demo(args):
with gr.Blocks() as demo:
gr.Markdown(
"""<p align="center"><img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/assets/blog/qwenaudio/qwen2audio_logo.png" style="height: 80px"/><p>""")
gr.Markdown("""<center><font size=8>Qwen2-Audio-Instruct Bot</center>""")
gr.Markdown(
"""\
<center><font size=3>This WebUI is based on Qwen2-Audio-Instruct, developed by Alibaba Cloud. \
</center>""")
gr.Markdown("""\
<center><font size=4>Qwen2-Audio <a href="https://modelscope.cn/models/qwen/Qwen2-Audio-7B">π€ </a>
| <a href="https://huggingface.co/Qwen/Qwen2-Audio-7B">π€</a>  ο½
Qwen2-Audio-Instruct <a href="https://modelscope.cn/models/qwen/Qwen2-Audio-7B-Instruct">π€ </a> |
<a href="https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct">π€</a>  ο½
 <a href="https://github.com/QwenLM/Qwen2-Audio">Github</a></center>""")
chatbot = gr.Chatbot(label='Qwen2-Audio-7B-Instruct', height=750)
with gr.Row():
text_input = gr.Textbox(
show_label=False,
placeholder="Type your message here...",
container=False
)
audio_input = gr.Audio(
sources=["microphone", "upload"],
type="filepath"
)
with gr.Row():
submit_btn = gr.Button("π Submit")
empty_btn = gr.Button("π§Ή Clear History")
regen_btn = gr.Button("π€οΈ Regenerate")
task_history = gr.State([])
def process_input(text, audio, chatbot, history):
"""Process input with correct message formatting for Chatbot."""
content = []
message_text = []
if audio is not None:
content.append({'type': 'audio', 'audio_url': audio})
message_text.append(f"[Audio file uploaded]")
if text:
content.append({'type': 'text', 'text': text})
message_text.append(text)
history.append({"role": "user", "content": content})
# Format message for chatbot as a string instead of dict
chatbot.append([" ".join(message_text), None])
return "", None, chatbot, history
def predict(chatbot, task_history):
"""Generate a response from the model."""
print(f"{task_history=}")
print(f"{chatbot=}")
text = processor.apply_chat_template(task_history, add_generation_prompt=True, tokenize=False)
audios = []
for message in task_history:
if isinstance(message["content"], list):
for ele in message["content"]:
if ele["type"] == "audio":
audios.append(
librosa.load(ele['audio_url'], sr=processor.feature_extractor.sampling_rate, mono=True)[0]
)
if len(audios)==0:
audios=None
print(f"{text=}")
print(f"{audios=}")
inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
inputs["input_ids"] = inputs.input_ids.cuda()
generate_ids = model.generate(**inputs, max_length=256)
generate_ids = generate_ids[:, inputs.input_ids.size(1):]
response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
print(f"{response=}")
task_history.append({'role': 'assistant',
'content': response})
chatbot.append((None, response))
return chatbot, task_history
# Update event handlers for new input components
# def process_input(text, audio, chatbot, history):
# content = []
# if audio is not None:
# content.append({'type': 'audio', 'audio_url': audio})
# if text:
# content.append({'type': 'text', 'text': text})
#
# history.append({"role": "user", "content": content})
# chatbot.append([
# {"text": text, "audio": audio},
# None
# ])
# return "", None, chatbot, history
submit_btn.click(
fn=process_input,
inputs=[text_input, audio_input, chatbot, task_history],
outputs=[text_input, audio_input, chatbot, task_history]
).then(
predict,
[chatbot, task_history],
[chatbot, task_history],
show_progress=True
)
empty_btn.click(reset_state, outputs=[chatbot, task_history], show_progress=True)
regen_btn.click(regenerate, [chatbot, task_history], [chatbot, task_history], show_progress=True)
demo.queue().launch(
share=False,
inbrowser=args.inbrowser,
server_port=args.server_port,
server_name=args.server_name,
)
if __name__ == "__main__":
args = _get_args()
if args.cpu_only:
device_map = "cpu"
else:
device_map = "auto"
model = Qwen2AudioForConditionalGeneration.from_pretrained(
args.checkpoint_path,
torch_dtype="auto",
device_map=device_map,
resume_download=True,
).eval()
model.generation_config.max_new_tokens = 2048 # For chat.
print("generation_config", model.generation_config)
processor = AutoProcessor.from_pretrained(args.checkpoint_path, resume_download=True)
_launch_demo(args)
|