dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-28 00:05:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

Refactor voice recording and transcription to allow for specifying the language.

Browse source
This commit is contained in:
Paul Gauthier 2023-08-14 14:11:03 -03:00
parent f4e1c1010b
commit 23579d4741
2 changed files with 9 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

9
aider/commands.py
View file

@ -14,9 +14,14 @@ from .dump import dump # noqa: F401
class Commands: class Commands:
def __init__(self, io, coder): def __init__(self, io, coder, voice_language=None):
self.io = io self.io = io
self.coder = coder self.coder = coder
if voice_language == 'auto':
voice_language=None
self.voice_language = voice_language
self.tokenizer = tiktoken.encoding_for_model(coder.main_model.name) self.tokenizer = tiktoken.encoding_for_model(coder.main_model.name)
def is_command(self, inp): def is_command(self, inp):
@ -460,7 +465,7 @@ class Commands:
history = "\n".join(history) history = "\n".join(history)
dump(history) dump(history)
text = v.record_and_transcribe(history) text = v.record_and_transcribe(history, self.voice_language)
if text: if text:
self.io.add_to_input_history(text) self.io.add_to_input_history(text)
print() print()

4
aider/voice.py
View file

@ -60,7 +60,7 @@ class Voice:
except KeyboardInterrupt: except KeyboardInterrupt:
return return
def raw_record_and_transcribe(self, history): def raw_record_and_transcribe(self, history, language):
self.q = queue.Queue() self.q = queue.Queue()
filename = tempfile.mktemp(suffix=".wav") filename = tempfile.mktemp(suffix=".wav")
@ -77,7 +77,7 @@ class Voice:
file.write(self.q.get()) file.write(self.q.get())
with open(filename, "rb") as fh: with open(filename, "rb") as fh:
transcript = openai.Audio.transcribe("whisper-1", fh, prompt=history) transcript = openai.Audio.transcribe("whisper-1", fh, prompt=history, language=language)
text = transcript["text"] text = transcript["text"]
return text return text