GenAI – Audio File Chunking Process
Table Of Content:
- How To Chunk Audio Files ?
(1) Reference Links
https://github.com/infiniflow/ragflow/blob/main/rag/app/audio.py(2) How To Chunk Audio Files ?
Imported File Links:
https://github.com/infiniflow/ragflow/blob/main/api/db/__init__.pyhttps://github.com/infiniflow/ragflow/blob/main/rag/nlp/rag_tokenizer.pyhttps://github.com/infiniflow/ragflow/blob/main/api/db/services/llm_service.pyhttps://github.com/infiniflow/ragflow/blob/main/rag/nlp/__init__.pyimport re
from api.db import LLMType
from rag.nlp import rag_tokenizer
from api.db.services.llm_service import LLMBundle
from rag.nlp import tokenize
def chunk(filename, binary, tenant_id, lang, callback=None, **kwargs):
doc = {
"docnm_kwd": filename,
"title_tks": rag_tokenizer.tokenize(re.sub(r"\.[a-zA-Z]+$", "", filename))
}
doc["title_sm_tks"] = rag_tokenizer.fine_grained_tokenize(doc["title_tks"])
# is it English
eng = lang.lower() == "english" # is_english(sections)
try:
callback(0.1, "USE Sequence2Txt LLM to transcription the audio")
seq2txt_mdl = LLMBundle(tenant_id, LLMType.SPEECH2TEXT, lang=lang)
ans = seq2txt_mdl.transcription(binary)
callback(0.8, "Sequence2Txt LLM respond: %s ..." % ans[:32])
tokenize(doc, ans, eng)
return [doc]
except Exception as e:
callback(prog=-1, msg=str(e))
return [](3) Description
(4) Input Parameters Explained
