diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml index 8b5cca86..da14a6a4 100644 --- a/main/xiaozhi-server/config.yaml +++ b/main/xiaozhi-server/config.yaml @@ -232,6 +232,9 @@ ASR: appid: 你的火山引擎语音合成服务appid access_token: 你的火山引擎语音合成服务access_token cluster: volcengine_input_common + # 热词、替换词使用流程:https://www.volcengine.com/docs/6561/155738 + boosting_table_name: (选填)你的热词文件名称 + correct_table_name: (选填)你的替换词文件名称 output_dir: tmp/ TencentASR: # token申请地址:https://console.cloud.tencent.com/cam/capi diff --git a/main/xiaozhi-server/core/providers/asr/doubao.py b/main/xiaozhi-server/core/providers/asr/doubao.py index 6fba472c..755a19b7 100644 --- a/main/xiaozhi-server/core/providers/asr/doubao.py +++ b/main/xiaozhi-server/core/providers/asr/doubao.py @@ -88,6 +88,8 @@ class ASRProvider(ASRProviderBase): self.appid = config.get("appid") self.cluster = config.get("cluster") self.access_token = config.get("access_token") + self.boosting_table_name = config.get("boosting_table_name") + self.correct_table_name = config.get("correct_table_name") self.output_dir = config.get("output_dir") self.delete_audio_file = delete_audio_file @@ -136,7 +138,13 @@ class ASRProvider(ASRProviderBase): "user": { "uid": str(uuid.uuid4()), }, - "request": {"reqid": reqid, "show_utterances": False, "sequence": 1}, + "request": { + "reqid": reqid, + "show_utterances": False, + "sequence": 1, + "boosting_table_name": self.boosting_table_name, + "correct_table_name": self.correct_table_name, + }, "audio": { "format": "raw", "rate": 16000, @@ -232,14 +240,6 @@ class ASRProvider(ASRProviderBase): return pcm_data - @staticmethod - def read_wav_info(data: io.BytesIO = None) -> (int, int, int, int, int): - with io.BytesIO(data) as _f: - wave_fp = wave.open(_f, "rb") - nchannels, sampwidth, framerate, nframes = wave_fp.getparams()[:4] - wave_bytes = wave_fp.readframes(nframes) - return nchannels, sampwidth, framerate, nframes, len(wave_bytes) - @staticmethod def slice_data(data: bytes, chunk_size: int) -> (list, bool): """