Whisper Large V3 Russian Ties Podlodka V1.0

🚀 俄语语音识别合并模型

本项目是基于TIES方法合并的俄语语音识别模型，使用了多个基础模型和数据集，可用于自动语音识别（ASR）任务。

🚀 快速开始

模型信息

新版本信息

新版本已发布：Apel-sin/whisper-large-v3-russian-ties-podlodka-v1.2

📚 详细文档

模型合并细节

此模型使用TIES合并方法进行合并，具体配置如下：

method: ties
parameters:
  ties_density: 0.85
  encoder_weights:
    - 0.65
    - 0.35
  decoder_weights:
    - 0.6
    - 0.4
models:
  model_a: "/mnt/cloud/llm/whisper/whisper-large-v3-russian"
  model_b: "/mnt/cloud/llm/whisper/whisper-large-v3-ru-podlodka"
output_dir: "/mnt/cloud/llm/whisper/whisper-large-v3-russian-ties-podlodka"

简单API服务器

该模型可与简单的OpenAI兼容API服务器一起使用：https://github.com/kreolsky/whisper-api-server/

💻 使用示例

基础用法

为了处理电话通话，强烈建议在进行自动语音识别（ASR）之前对录音进行预处理并调整音量。例如，可以使用以下命令：

sox record.wav -r 8000 record-normalized.wav norm -0.5 compand 0.3,1 -90,-90,-70,-50,-40,-15,0,0 -7 0 0.15

然后，ASR代码示例如下：

import torch
from transformers import WhisperForConditionalGeneration, WhisperProcessor, pipeline

torch_dtype = torch.bfloat16 # set your preferred type here 

device = 'cpu'
if torch.cuda.is_available():
    device = 'cuda'
elif torch.backends.mps.is_available():
    device = 'mps'
    setattr(torch.distributed, "is_initialized", lambda : False) # monkey patching
device = torch.device(device)

whisper = WhisperForConditionalGeneration.from_pretrained(
    "antony66/whisper-large-v3-russian", torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True,
    # add attn_implementation="flash_attention_2" if your GPU supports it
)

processor = WhisperProcessor.from_pretrained("antony66/whisper-large-v3-russian")

asr_pipeline = pipeline(
    "automatic-speech-recognition",
    model=whisper,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    max_new_tokens=256,
    chunk_length_s=30,
    batch_size=16,
    return_timestamps=True,
    torch_dtype=torch_dtype,
    device=device,
)

# read your wav file into variable wav. For example:
from io import BufferIO
wav = BytesIO()
with open('record-normalized.wav', 'rb') as f:
    wav.write(f.read())
wav.seek(0)

# get the transcription
asr = asr_pipeline(wav, generate_kwargs={"language": "russian", "max_new_tokens": 256}, return_timestamps=False)

print(asr['text'])

🔧 开发进度

目前该模型仍在开发中，目标是尽可能对其进行微调，以用于电话通话的语音识别。如果您想贡献代码，并且知道或拥有任何优质数据集，请告知。非常感谢您的帮助。