Hugging Face's logo

asadfgglie
/
faster-whisper-large-v3-zh-TW

Automatic Speech Recognition
Chinese
ctranslate2
audio
Model card Files Community
faster-whisper-large-v3-zh-TW / README.md
asadfgglie's picture
asadfgglie
Update README.md
f3c9e64 verified
preview code
|
raw
history blame contribute delete
1.62 kB
metadata
language:
  - zh
base_model:
  - JacobLinCool/whisper-large-v3-turbo-common_voice_19_0-zh-TW
pipeline_tag: automatic-speech-recognition
tags:
  - audio
  - automatic-speech-recognition
library_name: ctranslate2

asadfgglie/faster-whisper-large-v3-zh-TW

此模型是將JacobLinCool/whisper-large-v3-turbo-common_voice_19_0-zh-TW 轉換成CTranslate2格式的模型，可以在faster-whisper中使用。

Example 

from faster_whisper import WhisperModel

model = WhisperModel("asadfgglie/faster-whisper-large-v3-zh-TW")

segments, info = model.transcribe("audio.mp3")
for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

Conversion details

原始模型是根據以下指令轉換:

ct2-transformers-converter --output_dir faster-whisper-large-v3-zh-TW \
 --model JacobLinCool/whisper-large-v3-turbo-common_voice_19_0-zh-TW \
 --copy_files preprocessor_config.json

在轉換完成後，請記得自行到原始模型的model card中下載tokenizer.json。 (因為JacobLinCool/whisper-large-v3-turbo-common_voice_19_0-zh-TW的repo中沒有，而faster_whishper又需要這個酷東東來做tokenizer)

如果有需要，你可以在轉換指令中添加--quantization float16來指定量化精度。不過在推理時你依舊可以使用compute_type參數來進一步量化/去除量化。