-
Notifications
You must be signed in to change notification settings - Fork 8k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'master' of github.com:binary-husky/chatgpt_academic
- Loading branch information
Showing
21 changed files
with
1,531 additions
and
192 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -150,3 +150,4 @@ request_llm/jittorllms | |
| multi-language | ||
| request_llm/moss | ||
| media | ||
| flagged | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,93 @@ | ||
| import time, threading, json | ||
|
|
||
|
|
||
| class AliyunASR(): | ||
|
|
||
| def test_on_sentence_begin(self, message, *args): | ||
| # print("test_on_sentence_begin:{}".format(message)) | ||
| pass | ||
|
|
||
| def test_on_sentence_end(self, message, *args): | ||
| # print("test_on_sentence_end:{}".format(message)) | ||
| message = json.loads(message) | ||
| self.parsed_sentence = message['payload']['result'] | ||
| self.event_on_entence_end.set() | ||
| print(self.parsed_sentence) | ||
|
|
||
| def test_on_start(self, message, *args): | ||
| # print("test_on_start:{}".format(message)) | ||
| pass | ||
|
|
||
| def test_on_error(self, message, *args): | ||
| # print("on_error args=>{}".format(args)) | ||
| pass | ||
|
|
||
| def test_on_close(self, *args): | ||
| self.aliyun_service_ok = False | ||
| pass | ||
|
|
||
| def test_on_result_chg(self, message, *args): | ||
| # print("test_on_chg:{}".format(message)) | ||
| message = json.loads(message) | ||
| self.parsed_text = message['payload']['result'] | ||
| self.event_on_result_chg.set() | ||
|
|
||
| def test_on_completed(self, message, *args): | ||
| # print("on_completed:args=>{} message=>{}".format(args, message)) | ||
| pass | ||
|
|
||
|
|
||
| def audio_convertion_thread(self, uuid): | ||
| # 在一个异步线程中采集音频 | ||
| import nls # pip install git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git | ||
| import tempfile | ||
| from scipy import io | ||
| from toolbox import get_conf | ||
| from .audio_io import change_sample_rate | ||
| from .audio_io import RealtimeAudioDistribution | ||
| NEW_SAMPLERATE = 16000 | ||
| rad = RealtimeAudioDistribution() | ||
| rad.clean_up() | ||
| temp_folder = tempfile.gettempdir() | ||
| TOKEN, APPKEY = get_conf('ALIYUN_TOKEN', 'ALIYUN_APPKEY') | ||
| self.aliyun_service_ok = True | ||
| URL="wss://nls-gateway.aliyuncs.com/ws/v1" | ||
| sr = nls.NlsSpeechTranscriber( | ||
| url=URL, | ||
| token=TOKEN, | ||
| appkey=APPKEY, | ||
| on_sentence_begin=self.test_on_sentence_begin, | ||
| on_sentence_end=self.test_on_sentence_end, | ||
| on_start=self.test_on_start, | ||
| on_result_changed=self.test_on_result_chg, | ||
| on_completed=self.test_on_completed, | ||
| on_error=self.test_on_error, | ||
| on_close=self.test_on_close, | ||
| callback_args=[uuid.hex] | ||
| ) | ||
|
|
||
| r = sr.start(aformat="pcm", | ||
| enable_intermediate_result=True, | ||
| enable_punctuation_prediction=True, | ||
| enable_inverse_text_normalization=True) | ||
|
|
||
| while not self.stop: | ||
| # time.sleep(self.capture_interval) | ||
| audio = rad.read(uuid.hex) | ||
| if audio is not None: | ||
| # convert to pcm file | ||
| temp_file = f'{temp_folder}/{uuid.hex}.pcm' # | ||
| dsdata = change_sample_rate(audio, rad.rate, NEW_SAMPLERATE) # 48000 --> 16000 | ||
| io.wavfile.write(temp_file, NEW_SAMPLERATE, dsdata) | ||
| # read pcm binary | ||
| with open(temp_file, "rb") as f: data = f.read() | ||
| # print('audio len:', len(audio), '\t ds len:', len(dsdata), '\t need n send:', len(data)//640) | ||
| slices = zip(*(iter(data),) * 640) # 640个字节为一组 | ||
| for i in slices: sr.send_audio(bytes(i)) | ||
| else: | ||
| time.sleep(0.1) | ||
|
|
||
| if not self.aliyun_service_ok: | ||
| self.stop = True | ||
| self.stop_msg = 'Aliyun音频服务异常，请检查ALIYUN_TOKEN和ALIYUN_APPKEY是否过期。' | ||
| r = sr.stop() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,51 @@ | ||
| import numpy as np | ||
| from scipy import interpolate | ||
|
|
||
| def Singleton(cls): | ||
| _instance = {} | ||
|
|
||
| def _singleton(*args, **kargs): | ||
| if cls not in _instance: | ||
| _instance[cls] = cls(*args, **kargs) | ||
| return _instance[cls] | ||
|
|
||
| return _singleton | ||
|
|
||
|
|
||
| @Singleton | ||
| class RealtimeAudioDistribution(): | ||
| def __init__(self) -> None: | ||
| self.data = {} | ||
| self.max_len = 1024*1024 | ||
| self.rate = 48000 # 只读，每秒采样数量 | ||
|
|
||
| def clean_up(self): | ||
| self.data = {} | ||
|
|
||
| def feed(self, uuid, audio): | ||
| self.rate, audio_ = audio | ||
| # print('feed', len(audio_), audio_[-25:]) | ||
| if uuid not in self.data: | ||
| self.data[uuid] = audio_ | ||
| else: | ||
| new_arr = np.concatenate((self.data[uuid], audio_)) | ||
| if len(new_arr) > self.max_len: new_arr = new_arr[-self.max_len:] | ||
| self.data[uuid] = new_arr | ||
|
|
||
| def read(self, uuid): | ||
| if uuid in self.data: | ||
| res = self.data.pop(uuid) | ||
| print('\r read-', len(res), '-', max(res), end='', flush=True) | ||
| else: | ||
| res = None | ||
| return res | ||
|
|
||
| def change_sample_rate(audio, old_sr, new_sr): | ||
| duration = audio.shape[0] / old_sr | ||
|
|
||
| time_old = np.linspace(0, duration, audio.shape[0]) | ||
| time_new = np.linspace(0, duration, int(audio.shape[0] * new_sr / old_sr)) | ||
|
|
||
| interpolator = interpolate.interp1d(time_old, audio.T) | ||
| new_audio = interpolator(time_new).T | ||
| return new_audio.astype(np.int16) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.